Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+merged/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,144 @@
+---
+license: other
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: google/gemma-7b
+model-index:
+- name: out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: google/gemma-7b
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+ 
+load_in_8bit: false
+load_in_4bit: true
+strict: false
+ 
+datasets:
+  - path: combined_file.json
+    ds_type: json
+    type: alpaca
+val_set_size: 0.1
+output_dir: ./out
+ 
+adapter: qlora
+lora_r: 32
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_target_modules:
+  - q_proj
+  - v_proj
+  - v_proj
+  - o_proj
+  - gate_proj
+  - down_proj
+  - up_proj
+ 
+sequence_len: 4096
+sample_packing: false
+pad_to_sequence_len: false
+ 
+wandb_project: gemma_results
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+ 
+ 
+gradient_accumulation_steps: 3
+micro_batch_size: 2
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 5e-5
+ 
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+ 
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+ 
+warmup_ratio: 0.1
+evals_per_epoch: 1
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+```
+
+</details><br>
+
+# out
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0418
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 6
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 2092
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.1309        | 1.0   | 20924 | 1.0418          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67099cd5a59e6624588db6ab83b1ccb89c5d81bdf80f8ff61028008ab02b63a
+size 200078074

checkpoint-20924/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-7b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

checkpoint-20924/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

checkpoint-20924/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee09e2d41068666d5ded04ec0edcd2ddc24f4c4f426d30fe364604d001b33c4
+size 200068904

checkpoint-20924/global_step20924/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0af6ac094e2b36e74066c3cca7b2da6a7d6772b3c331ba60ac8ee662c0abfe
+size 600488016

checkpoint-20924/global_step20924/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc9097c77de665bf793e1b8b17b604145d8a8323b7189dbd4ac779a93f76c2b
+size 1896781222

checkpoint-20924/latest

@@ -0,0 +1 @@
+global_step20924

checkpoint-20924/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1747f416e3f3d8c72501521e7ac5767701ef9ba9323a54c32b0e3904781afa
+size 14244

checkpoint-20924/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787ca803b53834ca399a57cc809089827fcbe29b9acebd2592f139c205511220
+size 1064

checkpoint-20924/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8db9ea471f520c9b5c751cdf5400d22f96636b1d4a2c2490fb1a17a909c9a82
+size 6456

checkpoint-20924/zero_to_fp32.py

@@ -0,0 +1,592 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

merged/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

merged/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.0.dev0"
+}

merged/pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1d6f7dfaacfa8001f31843684cd9f9fa137a48d099ee8a3521719dc5fc76d4
+size 4995511092

merged/pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a1425601ebb54efd8b6ed8517de3e32e1f06520e0f805a7ab19faaf3858ac5b
+size 4982972660

merged/pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89122a6662909321cd39ca2a5735cf63105490806561bb0d875238b13e31455b
+size 4982972724

merged/pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b70feb4632f68ffbb5e232c65f3d39268de0e890efeffecc28da7ad91a3c70bb
+size 2113996412

merged/pytorch_model.bin.index.json

@@ -0,0 +1,262 @@
+{
+  "metadata": {
+    "total_size": 17075361792
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00004.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}

merged/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

merged/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

merged/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

merged/tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}