Upload folder using huggingface_hub

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

l3step1.json

@@ -0,0 +1,6 @@
+{
+    "train_micro_batch_size_per_gpu": 16,
+    "gradient_accumulation_steps": 4,
+    "gradient_clipping": 1.0,
+    "steps_per_print": 1
+}

l3step1.toml

@@ -0,0 +1,114 @@
+# Paths
+model = './mnstage2'
+output_dir = './MNI-stage3'
+
+# Lora configuration
+# can use full_fine_tune=true and load_in_4bit=false to train the whole model instead of a LoRA
+full_fine_tune = true
+load_in_4bit = false
+# lora_rank = 8
+# lora_alpha = 256
+# lora_dropout = 0.05
+# Train only specific modules. This is passed to the parameter of the same name in the LoraConfig.
+# If not set, adapt all linear modules.
+# Note, this ALSO affects full fine tuning. In that case, if this is set, only weights containing one
+# of these keys as substring will have requires_grad.
+# target_modules = ['q_proj', 'k_proj', 'v_proj', 'o_proj']
+
+# can specify layers to adapt with LoRA if you want
+#layers_to_transform = '16:31'
+
+# for Mixtral, set the load balancing coefficient
+#load_balancing_loss_coef = 0.02
+
+# Optimization configuration
+epochs = 5
+lr_scheduler = 'constant'  # can also be 'constant'
+warmup_steps = 1
+
+# might be useful if resuming from a checkpoint and you want to change the LR and force it to something
+#force_constant_lr = 5e-5
+
+# hard clamp the magnitude of the LoRA weights
+#scale_weight_norms = 1.0
+
+# dynamic batch size, targeting this many tokens per batch, per device
+# if set, completely ignores the batch size in the deepspeed JSON config file
+# can be thought of as a replacement for sample packing
+batch_size_tokens = 4096
+
+# Performance settings
+pipeline_stages = 4  # number of pipeline parallel stages, must evenly divide the number of GPUs you launch the script with
+logging_steps = 1  # how often to log in Tensorboard
+eval_steps = 100000
+save_steps = 200000
+checkpoint_every_n_minutes = 960
+eval_before_first_step = true  # do an eval before any training happens
+bnb_compute_dtype = 'bfloat16'
+lora_weight_dtype = 'bfloat16'
+# Can have the saved weights be different dtype. Don't need to set this. Could be useful for
+# training in float32 but saving with float16.
+#save_dtype = 'bfloat16'
+use_double_quant = false
+
+# sort examples by length before dividing them into batches
+# this makes all examples in a batch approximately the same length, to minimize padding
+# the batches are still shuffled after that
+# you should probably always have this set to true
+group_by_length = true
+
+activation_checkpointing = true
+# Keep MLP weights on system RAM until they are needed. Can save a ton of VRAM with a
+# moderate hit to performance. If using an MoE model, this can also be an integer, in
+# which case only that many experts are offloaded (tradeoff between VRAM and speed).
+# offload_mlp_to_cpu = true
+
+# Resume a prior run
+# if true, we attempt to resume training from the most recent directory inside output_dir (the directory names are timestamps)
+# so, to resume, just run the exact same command but set this to true first
+resume_from_checkpoint = false
+
+# Loading the optimizer states seems to cause some kind of unavoidable VRAM memory leak.
+# It's very small, only about 0.2 GB in cases I've seen. But if you are very close to the
+# limit, it can cause resuming from checkpoint to OOM. As a last resort, you can uncomment
+# this to not load the optimizer states and hopefully the resumption won't OOM.
+#load_optimizer_states = false
+# Dataset configuration
+
+# How to combine multiple datasets if you have more than one.
+# Can be 'concatenate' or 'interleave'. Will be 'concatenate' if not set.
+dataset_combination_mode = 'interleave'
+# When to stop interleaving datasets when using mode 'interleave'. Either 'first_exhausted' or 'all_exhausted'.
+# Default if not set: 'first_exhausted'
+dataset_interleave_stopping_strategy = 'all_exhausted'
+# Can set this lower than training, so we don't drop as many examples when trying to make equal-sized batches.
+# Default if not set: same as training GAS.
+eval_gradient_accumulation_steps = 1
+
+[optimizer]
+# AdamW or AdamW8bit
+type = 'AdamW8bit'
+lr = 3e-6
+beta1 = 0.9
+beta2 = 0.99
+weight_decay = 0.1
+
+[[datasets]]
+# Arbitrary name, used only for separately logging eval metrics. Will be dataset0, dataset1, etc if not set.
+name = 'alpaca'
+dataset_type = 'textfile'
+dataset_path = 'nucorpus.json'
+sequence_len = 512
+eval_size = 0.02
+# Relative sampling weight, when using combination mode 'interleave'. Will be 1 if not set.
+sample_weight = 1
+
+# In addition to using eval_size which splits off some of the dataset, we can have completely separate datasets for eval.
+# This can be useful if you're training on raw text data, so that the eval set remains completely fixed, even if
+# you change training sequence_len, etc.
+# This is just an example, typically you wouldn't have this overlap a training dataset.
+# [[eval_datasets]]
+# name = 'capybara'
+# dataset_type = 'axolotl'
+# dataset_path = 'examples/capybara.yml'
+# sequence_len = 2048

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b459f0c73924e7f4769b4ee33336db8263d785b67f3edcd6e9a4a8db0c9fd12e
+size 4970444368

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064c6047ede455f504972dfe580ebb89dc981e6b8a9e7c9446e6090c017b7f87
+size 4949408352

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4663614b420a55a1046cf70738f42dd01097257f557073542340652c8099f77
+size 4907529408

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5c735806209c6dfcf4c4d39475cd4bad33cd98796706ef03a14e11b7a5fd96
+size 4865553584

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062260b5e627054397e952019db6dac07e794c23386fb3fbbdd3ef223b1b0132
+size 4802671384

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 24495564800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.norm.weight": "model-00004-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}