Upload folder using huggingface_hub

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    75864,
+    75869
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "use_cache": true,
+  "vocab_size": 76800
+}

conversion_to_hf.log

@@ -0,0 +1,241 @@
+Loaded loader_megatron_core as the loader.
+Loaded saver_llama2_hf_bf as the saver.
+Starting saver...
+Starting loader...
+fused_indices_to_multihot has reached end of life. Please migrate to a non-experimental function.
+/usr/local/lib/python3.12/dist-packages/modelopt/torch/utils/import_utils.py:31: UserWarning: Failed to import apex plugin due to: AttributeError("module 'transformers.modeling_utils' has no attribute 'Conv1D'"). You may ignore this warning if you do not need this plugin.
+  warnings.warn(
+/usr/local/lib/python3.12/dist-packages/modelopt/torch/utils/import_utils.py:31: UserWarning: Failed to import huggingface plugin due to: AttributeError("module 'transformers.modeling_utils' has no attribute 'Conv1D'"). You may ignore this warning if you do not need this plugin.
+  warnings.warn(
+/usr/local/lib/python3.12/dist-packages/modelopt/torch/utils/import_utils.py:31: UserWarning: Failed to import megatron plugin due to: AttributeError("module 'transformers.modeling_utils' has no attribute 'Conv1D'"). You may ignore this warning if you do not need this plugin.
+  warnings.warn(
+Setting num_layers to 80 from checkpoint
+Setting hidden_size to 5120 from checkpoint
+Setting ffn_hidden_size to 27648 from checkpoint
+Setting seq_length to 131072 from checkpoint
+Setting num_attention_heads to 40 from checkpoint
+Setting num_query_groups to 8 from checkpoint
+Setting group_query_attention to True from checkpoint
+Setting kv_channels to 128 from checkpoint
+Setting max_position_embeddings to 131072 from checkpoint
+Setting position_embedding_type to rope from checkpoint
+Setting add_position_embedding to True from checkpoint
+Setting use_rotary_position_embeddings to True from checkpoint
+Setting rotary_base to 500000 from checkpoint
+Setting rotary_percent to 1.0 from checkpoint
+Setting rotary_interleaved to False from checkpoint
+Setting add_bias_linear to False from checkpoint
+Setting add_qkv_bias to False from checkpoint
+Setting squared_relu to False from checkpoint
+Setting swiglu to True from checkpoint
+Setting untie_embeddings_and_output_weights to True from checkpoint
+Setting apply_layernorm_1p to False from checkpoint
+Setting normalization to RMSNorm from checkpoint
+Setting apply_query_key_layer_scaling to False from checkpoint
+Setting attention_dropout to 0.0 from checkpoint
+Setting hidden_dropout to 0.0 from checkpoint
+Checkpoint did not provide arguments hybrid_override_pattern
+Checkpoint did not provide arguments spec
+Setting hybrid_attention_ratio to 0.0 from checkpoint
+Setting hybrid_mlp_ratio to 0.0 from checkpoint
+Checkpoint did not provide arguments num_experts
+Setting moe_layer_freq to 1 from checkpoint
+Setting moe_router_topk to 2 from checkpoint
+Setting moe_router_pre_softmax to False from checkpoint
+Setting moe_grouped_gemm to False from checkpoint
+Checkpoint did not provide arguments moe_shared_expert_intermediate_size
+Setting mamba_state_dim to 128 from checkpoint
+Setting mamba_head_dim to 64 from checkpoint
+Setting mamba_num_groups to 8 from checkpoint
+Checkpoint did not provide arguments mamba_num_heads
+Setting is_hybrid_model to False from checkpoint
+Checkpoint did not provide arguments heterogeneous_layers_config_path
+Checkpoint did not provide arguments heterogeneous_layers_config_encoded_json
+Setting tokenizer_type to SFTTokenizer from checkpoint
+Setting tokenizer_model to /cpfs01/users/wzhang/iquest-coder-v1.1/RepoData-Ucoder-32B-128k-from2.5.2/97.09B_instruct_iquest-coder from checkpoint
+Checkpoint did not provide arguments tiktoken_pattern
+Setting padded_vocab_size to 76800 from checkpoint
+INFO:megatron.core.num_microbatches_calculator:setting number of microbatches to constant 1
+WARNING: one_logger package is required to enable e2e metrics tracking. please go to https://confluence.nvidia.com/display/MLWFO/Package+Repositories for details to install it
+building GPT model ...
+(TP, PP) mismatch after resume ((1, 1) vs (8, 1) from checkpoint): RNG state will be ignored
+sharded_state_dict metadata loaded from the checkpoint: {'distrib_optim_sharding_type': 'dp_reshardable', 'singleton_local_shards': False, 'chained_optim_avoid_prefix': True}
+Job sharding has changed: Rerun state will be ignored
+ loading distributed checkpoint from /tmp/megatron_convert_iter985_node0_pid360_19ab7eb5 at iteration 985
+/volume/pt-train/users/wzhang/wjj-workspace/code-sft/src/training/Megatron-LM/megatron/core/dist_checkpointing/strategies/torch.py:956: FutureWarning: `load_state_dict` is deprecated and will be removed in future versions. Please use `load` instead.
+  checkpoint.load_state_dict(
+/usr/local/lib/python3.12/dist-packages/torch/distributed/checkpoint/planner_helpers.py:406: FutureWarning: Please use DTensor instead and we are deprecating ShardedTensor.
+  device = getattr(value, "device", None)
+/usr/local/lib/python3.12/dist-packages/torch/distributed/checkpoint/default_planner.py:454: FutureWarning: Please use DTensor instead and we are deprecating ShardedTensor.
+  and md.size != obj.size()
+ checkpoint version 3.0
+  successfully loaded checkpoint from /tmp/megatron_convert_iter985_node0_pid360_19ab7eb5 [ t 1/1, p 1/1 ] at iteration 985
+sending embeddings
+sending transformer layer 0
+sending transformer layer 1
+sending transformer layer 2
+sending transformer layer 3
+sending transformer layer 4
+sending transformer layer 5
+sending transformer layer 6
+sending transformer layer 7
+sending transformer layer 8
+sending transformer layer 9
+sending transformer layer 10
+sending transformer layer 11
+sending transformer layer 12
+sending transformer layer 13
+sending transformer layer 14
+sending transformer layer 15
+sending transformer layer 16
+sending transformer layer 17
+sending transformer layer 18
+sending transformer layer 19
+sending transformer layer 20
+sending transformer layer 21
+sending transformer layer 22
+sending transformer layer 23
+sending transformer layer 24
+sending transformer layer 25
+sending transformer layer 26
+sending transformer layer 27
+fused_indices_to_multihot has reached end of life. Please migrate to a non-experimental function.
+sending transformer layer 28
+sending transformer layer 29
+sending transformer layer 30
+sending transformer layer 31
+sending transformer layer 32
+sending transformer layer 33
+sending transformer layer 34
+sending transformer layer 35
+sending transformer layer 36
+sending transformer layer 37
+received embeddings
+received transformer layer 0
+sending transformer layer 38
+received transformer layer 1
+received transformer layer 2
+received transformer layer 3
+received transformer layer 4
+sending transformer layer 39
+received transformer layer 5
+received transformer layer 6
+received transformer layer 7
+received transformer layer 8
+received transformer layer 9
+received transformer layer 10
+sending transformer layer 40
+received transformer layer 11
+received transformer layer 12
+received transformer layer 13
+sending transformer layer 41
+received transformer layer 14
+received transformer layer 15
+received transformer layer 16
+received transformer layer 17
+sending transformer layer 42
+received transformer layer 18
+sending transformer layer 43
+sending transformer layer 44
+sending transformer layer 45
+received transformer layer 19
+sending transformer layer 46
+sending transformer layer 47
+received transformer layer 20
+sending transformer layer 48
+sending transformer layer 49
+received transformer layer 21
+sending transformer layer 50
+sending transformer layer 51
+sending transformer layer 52
+received transformer layer 22
+sending transformer layer 53
+sending transformer layer 54
+received transformer layer 23
+sending transformer layer 55
+sending transformer layer 56
+sending transformer layer 57
+received transformer layer 24
+sending transformer layer 58
+sending transformer layer 59
+received transformer layer 25
+sending transformer layer 60
+sending transformer layer 61
+sending transformer layer 62
+received transformer layer 26
+sending transformer layer 63
+sending transformer layer 64
+sending transformer layer 65
+received transformer layer 27
+sending transformer layer 66
+sending transformer layer 67
+sending transformer layer 68
+sending transformer layer 69
+received transformer layer 28
+sending transformer layer 70
+sending transformer layer 71
+received transformer layer 29
+sending transformer layer 72
+sending transformer layer 73
+sending transformer layer 74
+received transformer layer 30
+sending transformer layer 75
+sending transformer layer 76
+sending transformer layer 77
+received transformer layer 31
+sending transformer layer 78
+sending transformer layer 79
+sending final norm
+sending output layer
+Waiting for saver to complete...
+received transformer layer 32
+received transformer layer 33
+received transformer layer 34
+received transformer layer 35
+received transformer layer 36
+received transformer layer 37
+received transformer layer 38
+received transformer layer 39
+received transformer layer 40
+received transformer layer 41
+received transformer layer 42
+received transformer layer 43
+received transformer layer 44
+received transformer layer 45
+received transformer layer 46
+received transformer layer 47
+received transformer layer 48
+received transformer layer 49
+received transformer layer 50
+received transformer layer 51
+received transformer layer 52
+received transformer layer 53
+received transformer layer 54
+received transformer layer 55
+received transformer layer 56
+received transformer layer 57
+received transformer layer 58
+received transformer layer 59
+received transformer layer 60
+received transformer layer 61
+received transformer layer 62
+received transformer layer 63
+received transformer layer 64
+received transformer layer 65
+received transformer layer 66
+received transformer layer 67
+received transformer layer 68
+received transformer layer 69
+received transformer layer 70
+received transformer layer 71
+received transformer layer 72
+received transformer layer 73
+received transformer layer 74
+received transformer layer 75
+received transformer layer 76
+received transformer layer 77
+received transformer layer 78
+received transformer layer 79
+received final norm
+received output layer
+Saving model to disk ...

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [2, 75864, 75869],
+  "transformers_version": "4.55.4"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ffe70d9c2fa7d3590c3b5b0b8275216eb927a652b97abbbefc11754b2211bcd
+size 4813050528

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa42437620e37c877620132208e207a5e79ea86a262a4909080d4192503ac4c
+size 4875986024

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:006413bf793c2b3f2c3c6d6456e446a4f36ecdebeecb43acf960799139cf175d
+size 4875986056

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3de1fd2e8f1d3524657ee49c1589e90f832d093e677e60a1d7e41c0b6ed012
+size 4875986072

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0217383ce3fd43b931ccabe160bd55a59720beac52f14bf8c1ec955748e15256
+size 4875986072

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3c38c992cd8788b43a70dfb89e791945ea9293f91c5c7eae67344d8af2ee125
+size 4875986072

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67582c9e09f37b28bc26ecdc60b1d6a121cf07b3941f3d10738419ed517998a2
+size 4875986072

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34004e6b4f282b213c66121f668e93756f91e7b3f13a55c4d4c88ad9cd9cc59
+size 4875986072

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf61281f17d623db7a22aaec13eb1e51cbf8f8ef35f1034bd57d941ee422d8a
+size 4875986072

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c476875749e4289724a0f93c491502e52badb6971cbe4966b908cec5c91b503
+size 4875986072

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21169292e650e9dac4704244980a8bd5b16e30f14b5d49ae3ad872a679560998
+size 4875986072

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcbe8f756011457f1b30818cda1a35c87e79af024930ec7281c9d1b2865d1a
+size 4875986072

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2d0418245ed70bebd96a390d4eede7777332759bc705dbc34f0067b926658e
+size 4875986072

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84eacf4f2ff5f01874541a250c0ac6adefbc3d42cac379128aec6d7188fdd9b9
+size 4875986072

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b555a814e9524d2f168ba8ff45ed77e9e59878ebfb45d93d5a8b5a51e097cdc
+size 4875986072

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a43f97c2c5cc00668ec93d770309ecbd70eecbd353aaf3de9a2beecbd301adb
+size 4875986072

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2202ac91b6f81af0644b539c097af37af5701d2d44418aa3dc3846e8a53e6d5
+size 1635810072

model.safetensors.index.json

@@ -0,0 +1,731 @@
+{
+  "metadata": {
+    "total_parameters": 39794283520,
+    "total_size": 79588567040
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.norm.weight": "model-00017-of-00017.safetensors"
+  }
+}

tokenization_neo.py

@@ -0,0 +1,246 @@
+# Copyright 2024 NEO Inc. All Rights Reserved.
+
+# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
+#
+# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
+# and OPT implementations in this library. It has been modified from its
+# original forms to accommodate minor architectural differences compared
+# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+from shutil import copyfile
+from typing import Any, Dict, List, Optional, Tuple
+
+import sentencepiece as spm
+
+from transformers.tokenization_utils import AddedToken, PreTrainedTokenizer
+from transformers.utils import logging
+
+
+logger = logging.get_logger(__name__)
+
+VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}
+
+PRETRAINED_VOCAB_FILES_MAP = {
+    "vocab_file": {},
+    "tokenizer_file": {},
+}
+PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {}
+
+
+class NEOTokenizer(PreTrainedTokenizer):
+    """
+    Construct a NEO tokenizer. Based on byte-level Byte-Pair-Encoding.
+    Args:
+        vocab_file (`str`):
+            Path to the vocabulary file.
+    """
+
+    vocab_files_names = VOCAB_FILES_NAMES
+    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
+    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
+    model_input_names = ["input_ids", "attention_mask"]
+
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="<unk>",
+        bos_token="<s>",
+        eos_token="</s>",
+        pad_token=None,
+        sp_model_kwargs: Optional[Dict[str, Any]] = None,
+        add_bos_token=True,
+        add_eos_token=False,
+        clean_up_tokenization_spaces=False,
+        **kwargs,
+    ):
+        self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
+        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
+        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
+        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
+        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token
+        
+        self.vocab_file = vocab_file
+        self.add_bos_token = add_bos_token
+        self.add_eos_token = add_eos_token
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(vocab_file)        
+        
+        super().__init__(
+            bos_token=bos_token,
+            eos_token=eos_token,
+            unk_token=unk_token,
+            pad_token=pad_token,
+            add_bos_token=add_bos_token,
+            add_eos_token=add_eos_token,
+            sp_model_kwargs=self.sp_model_kwargs,
+            clean_up_tokenization_spaces=clean_up_tokenization_spaces,
+            **kwargs,
+        )
+
+    def __getstate__(self):
+        state = self.__dict__.copy()
+        state["sp_model"] = None
+        return state
+
+    def __setstate__(self, d):
+        self.__dict__ = d
+        self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
+        self.sp_model.Load(self.vocab_file)
+
+    @property
+    def vocab_size(self):
+        """Returns vocab size"""
+        return self.sp_model.get_piece_size()
+
+    def get_vocab(self):
+        """Returns vocab as a dict"""
+        vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
+        vocab.update(self.added_tokens_encoder)
+        return vocab
+
+    def _tokenize(self, text):
+        """Returns a tokenized string."""
+        return self.sp_model.encode(text, out_type=str)
+
+    def _convert_token_to_id(self, token):
+        """Converts a token (str) in an id using the vocab."""
+        return self.sp_model.piece_to_id(token)
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        token = self.sp_model.IdToPiece(index)
+        return token
+
+    def convert_tokens_to_string(self, tokens):
+        """Converts a sequence of tokens (string) in a single string."""
+        current_sub_tokens = []
+        out_string = ""
+        prev_is_special = False
+        for i, token in enumerate(tokens):
+            # make sure that special tokens are not decoded using sentencepiece model
+            if token in self.all_special_tokens:
+                if not prev_is_special and i != 0:
+                    out_string += " "
+                out_string += self.sp_model.decode(current_sub_tokens) + token
+                prev_is_special = True
+                current_sub_tokens = []
+            else:
+                current_sub_tokens.append(token)
+                prev_is_special = False
+        out_string += self.sp_model.decode(current_sub_tokens)
+        return out_string
+
+    def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
+        """
+        Save the vocabulary and special tokens file to a directory.
+        Args:
+            save_directory (`str`):
+                The directory in which to save the vocabulary.
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        if not os.path.isdir(save_directory):
+            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
+            return
+        out_vocab_file = os.path.join(
+            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
+        )
+
+        if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
+            copyfile(self.vocab_file, out_vocab_file)
+        elif not os.path.isfile(self.vocab_file):
+            with open(out_vocab_file, "wb") as fi:
+                content_spiece_model = self.sp_model.serialized_model_proto()
+                fi.write(content_spiece_model)
+
+        return (out_vocab_file,)
+
+    def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = bos_token_id + token_ids_0 + eos_token_id
+
+        if token_ids_1 is not None:
+            output = output + bos_token_id + token_ids_1 + eos_token_id
+
+        return output
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer `prepare_for_model` method.
+        Args:
+            token_ids_0 (`List[int]`):
+                List of IDs.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
+                Whether or not the token list is already formatted with special tokens for the model.
+        Returns:
+            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+        if already_has_special_tokens:
+            return super().get_special_tokens_mask(
+                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
+            )
+
+        bos_token_id = [1] if self.add_bos_token else []
+        eos_token_id = [1] if self.add_eos_token else []
+
+        if token_ids_1 is None:
+            return bos_token_id + ([0] * len(token_ids_0)) + eos_token_id
+        return (
+            bos_token_id
+            + ([0] * len(token_ids_0))
+            + eos_token_id
+            + bos_token_id
+            + ([0] * len(token_ids_1))
+            + eos_token_id
+        )
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Creates a mask from the two sequences passed to be used in a sequence-pair classification task. An ALBERT
+        sequence pair mask has the following format:
+        ```
+        0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+        | first sequence    | second sequence |
+        ```
+        if token_ids_1 is None, only returns the first portion of the mask (0s).
+        Args:
+            token_ids_0 (`List[int]`):
+                List of ids.
+            token_ids_1 (`List[int]`, *optional*):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            `List[int]`: List of [token type IDs](../glossary#token-type-ids) according to the given sequence(s).
+        """
+        bos_token_id = [self.bos_token_id] if self.add_bos_token else []
+        eos_token_id = [self.eos_token_id] if self.add_eos_token else []
+
+        output = [0] * len(bos_token_id + token_ids_0 + eos_token_id)
+
+        if token_ids_1 is not None:
+            output += [1] * len(bos_token_id + token_ids_1 + eos_token_id)
+
+        return output
+
+

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3be68e090a927f31e0e378d7599b15c206dd47e4a73933775a746cc9c1cd91
+size 1345108

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "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": true,
+      "special": true
+    },
+    "75858": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75859": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75860": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75861": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75862": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75863": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75864": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75865": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75866": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75867": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75868": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75869": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75870": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75871": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "75872": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75873": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75874": {
+      "content": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75875": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75876": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75877": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75878": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75879": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|CLS|>",
+    "<|SEP|>",
+    "<|EOD|>",
+    "<|MASK|>",
+    "<|PAD|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|fim_pad|>",
+    "<|endoftext|>",
+    "<|repo_name|>",
+    "<|file_sep|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_neo.NEOTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- else %}\n        {{- 'You are IQuest-Coder, a helpful assistant developed by IQuest.' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {%- if tool.type == 'function' and tool.function %}\n            {%- set func = tool.function %}\n        {%- else %}\n            {%- set func = tool %}\n        {%- endif %}\n        {{- \"\\n<function>\\n<name>\" + func.name + \"</name>\" }}\n        {%- if func.description %}\n            {{- \"\\n<description>\" + func.description + \"</description>\" }}\n        {%- endif %}\n        {{- \"\\n<parameters>\" }}\n        {%- if func.parameters and func.parameters.properties %}\n            {%- for param_name, param_fields in func.parameters.properties.items() %}\n                {{- \"\\n<parameter>\" }}\n                {{- \"\\n<name>\" + param_name + \"</name>\" }}\n                {%- if param_fields.type %}\n                    {{- \"\\n<type>\" + param_fields.type + \"</type>\" }}\n                {%- endif %}\n                {%- if param_fields.description %}\n                    {{- \"\\n<description>\" + param_fields.description + \"</description>\" }}\n                {%- endif %}\n                {{- \"\\n</parameter>\" }}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"\\n</parameters>\\n</function>\" }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nIf you choose to call a function ONLY reply in the following format:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n</function>\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are IQuest-Coder, a helpful assistant developed by IQuest.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- set has_think = false %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n            {%- set has_think = true %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set has_think = true %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and has_think) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {%- if has_think %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tc = tool_call.function %}\n                {%- else %}\n                    {%- set tc = tool_call %}\n                {%- endif %}\n                {{- '<tool_call>\\n<function=' + tc.name + '>\\n' }}\n                {%- if tc.arguments is string %}\n                    {%- set args = tc.arguments | fromjson %}\n                {%- else %}\n                    {%- set args = tc.arguments %}\n                {%- endif %}\n                {%- for arg_name, arg_value in args.items() %}\n                    {{- '<parameter=' + arg_name + '>\\n' }}\n                    {%- if arg_value is string %}\n                        {{- arg_value }}\n                    {%- else %}\n                        {{- arg_value | tojson }}\n                    {%- endif %}\n                    {{- '\\n</parameter>\\n' }}\n                {%- endfor %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "NEOTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}