Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-116/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-116/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+---
+
+# 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 0.14.0

checkpoint-116/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-116/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61ca14faac3ef1cd1a6f2e635ddf85b1f3ba8493f5d2258ff823d1c9f575cf8
+size 1291899552

checkpoint-116/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-116/global_step116/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:bf5fd84ddf3eb4684b23cb2d0fcacbcda8ab53cc22df5eec1f9c5fbdbf153fe7
+size 7751120668

checkpoint-116/global_step116/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe79f7f70949cf4492a23269af1e06a4d2e3d20e4c179d5dc3edbcdf46622971
+size 1396311192

checkpoint-116/latest

@@ -0,0 +1 @@
+global_step116

checkpoint-116/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b97181da0f84373ef23b66f26c783554268727710008775bbf7b0813466f1a
+size 14244

checkpoint-116/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76832eb744eae9d7bb427d3b85660553e6106c1ab18411779a5aaf9c42e0b54a
+size 1064

checkpoint-116/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-116/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-116/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-116/trainer_state.json

@@ -0,0 +1,845 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 116,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008620689655172414,
+      "grad_norm": 30.156124114990234,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 3.946,
+      "step": 1
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 29.95058250427246,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 4.0398,
+      "step": 2
+    },
+    {
+      "epoch": 0.02586206896551724,
+      "grad_norm": 29.866586685180664,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 3.9303,
+      "step": 3
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 30.012300491333008,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 3.9637,
+      "step": 4
+    },
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 30.934751510620117,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 4.0617,
+      "step": 5
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 30.031415939331055,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 3.9659,
+      "step": 6
+    },
+    {
+      "epoch": 0.0603448275862069,
+      "grad_norm": 29.62813949584961,
+      "learning_rate": 3.5000000000000004e-07,
+      "loss": 3.9978,
+      "step": 7
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 31.0523681640625,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 4.0237,
+      "step": 8
+    },
+    {
+      "epoch": 0.07758620689655173,
+      "grad_norm": 28.83756446838379,
+      "learning_rate": 4.5000000000000003e-07,
+      "loss": 3.8214,
+      "step": 9
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 28.1810359954834,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 3.848,
+      "step": 10
+    },
+    {
+      "epoch": 0.09482758620689655,
+      "grad_norm": 28.367570877075195,
+      "learning_rate": 5.5e-07,
+      "loss": 3.7026,
+      "step": 11
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 27.66380500793457,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 3.6833,
+      "step": 12
+    },
+    {
+      "epoch": 0.11206896551724138,
+      "grad_norm": 27.496694564819336,
+      "learning_rate": 6.5e-07,
+      "loss": 3.762,
+      "step": 13
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 28.319055557250977,
+      "learning_rate": 7.000000000000001e-07,
+      "loss": 3.8867,
+      "step": 14
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 26.112581253051758,
+      "learning_rate": 7.5e-07,
+      "loss": 3.6278,
+      "step": 15
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 25.8245792388916,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 3.7957,
+      "step": 16
+    },
+    {
+      "epoch": 0.14655172413793102,
+      "grad_norm": 23.66245460510254,
+      "learning_rate": 8.500000000000001e-07,
+      "loss": 3.4384,
+      "step": 17
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 21.69405746459961,
+      "learning_rate": 9.000000000000001e-07,
+      "loss": 3.2602,
+      "step": 18
+    },
+    {
+      "epoch": 0.16379310344827586,
+      "grad_norm": 20.691402435302734,
+      "learning_rate": 9.500000000000001e-07,
+      "loss": 3.2486,
+      "step": 19
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 20.67167854309082,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 3.2401,
+      "step": 20
+    },
+    {
+      "epoch": 0.1810344827586207,
+      "grad_norm": 19.054428100585938,
+      "learning_rate": 1.0500000000000001e-06,
+      "loss": 3.0375,
+      "step": 21
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 18.890884399414062,
+      "learning_rate": 1.1e-06,
+      "loss": 2.9677,
+      "step": 22
+    },
+    {
+      "epoch": 0.19827586206896552,
+      "grad_norm": 18.61600112915039,
+      "learning_rate": 1.1500000000000002e-06,
+      "loss": 2.8387,
+      "step": 23
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 16.910585403442383,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 2.4914,
+      "step": 24
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 17.708385467529297,
+      "learning_rate": 1.25e-06,
+      "loss": 2.5361,
+      "step": 25
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 17.07745933532715,
+      "learning_rate": 1.3e-06,
+      "loss": 2.4098,
+      "step": 26
+    },
+    {
+      "epoch": 0.23275862068965517,
+      "grad_norm": 16.244144439697266,
+      "learning_rate": 1.3500000000000002e-06,
+      "loss": 2.2155,
+      "step": 27
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 16.11887550354004,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 2.0036,
+      "step": 28
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 16.034631729125977,
+      "learning_rate": 1.45e-06,
+      "loss": 1.8617,
+      "step": 29
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 15.437153816223145,
+      "learning_rate": 1.5e-06,
+      "loss": 1.7413,
+      "step": 30
+    },
+    {
+      "epoch": 0.2672413793103448,
+      "grad_norm": 14.188116073608398,
+      "learning_rate": 1.5500000000000002e-06,
+      "loss": 1.5002,
+      "step": 31
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 14.200998306274414,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.4469,
+      "step": 32
+    },
+    {
+      "epoch": 0.28448275862068967,
+      "grad_norm": 13.209551811218262,
+      "learning_rate": 1.6500000000000003e-06,
+      "loss": 1.3016,
+      "step": 33
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 12.631085395812988,
+      "learning_rate": 1.7000000000000002e-06,
+      "loss": 1.1522,
+      "step": 34
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 12.504134178161621,
+      "learning_rate": 1.75e-06,
+      "loss": 1.0058,
+      "step": 35
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 12.599784851074219,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.921,
+      "step": 36
+    },
+    {
+      "epoch": 0.31896551724137934,
+      "grad_norm": 11.577665328979492,
+      "learning_rate": 1.85e-06,
+      "loss": 0.8099,
+      "step": 37
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 10.465872764587402,
+      "learning_rate": 1.9000000000000002e-06,
+      "loss": 0.6565,
+      "step": 38
+    },
+    {
+      "epoch": 0.33620689655172414,
+      "grad_norm": 10.161813735961914,
+      "learning_rate": 1.9500000000000004e-06,
+      "loss": 0.5712,
+      "step": 39
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 8.384145736694336,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.4265,
+      "step": 40
+    },
+    {
+      "epoch": 0.35344827586206895,
+      "grad_norm": 7.072062015533447,
+      "learning_rate": 2.05e-06,
+      "loss": 0.409,
+      "step": 41
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 6.072140693664551,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 0.3263,
+      "step": 42
+    },
+    {
+      "epoch": 0.3706896551724138,
+      "grad_norm": 6.31119441986084,
+      "learning_rate": 2.15e-06,
+      "loss": 0.258,
+      "step": 43
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 6.619389057159424,
+      "learning_rate": 2.2e-06,
+      "loss": 0.2454,
+      "step": 44
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 6.546375751495361,
+      "learning_rate": 2.25e-06,
+      "loss": 0.2314,
+      "step": 45
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 5.219631671905518,
+      "learning_rate": 2.3000000000000004e-06,
+      "loss": 0.2006,
+      "step": 46
+    },
+    {
+      "epoch": 0.4051724137931034,
+      "grad_norm": 3.1164474487304688,
+      "learning_rate": 2.35e-06,
+      "loss": 0.1677,
+      "step": 47
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 1.872147798538208,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1339,
+      "step": 48
+    },
+    {
+      "epoch": 0.4224137931034483,
+      "grad_norm": 1.4775545597076416,
+      "learning_rate": 2.4500000000000003e-06,
+      "loss": 0.1218,
+      "step": 49
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 1.2931559085845947,
+      "learning_rate": 2.5e-06,
+      "loss": 0.1151,
+      "step": 50
+    },
+    {
+      "epoch": 0.4396551724137931,
+      "grad_norm": 1.3222297430038452,
+      "learning_rate": 2.55e-06,
+      "loss": 0.1164,
+      "step": 51
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 1.393062710762024,
+      "learning_rate": 2.6e-06,
+      "loss": 0.1053,
+      "step": 52
+    },
+    {
+      "epoch": 0.45689655172413796,
+      "grad_norm": 1.0838805437088013,
+      "learning_rate": 2.6500000000000005e-06,
+      "loss": 0.105,
+      "step": 53
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 0.954925537109375,
+      "learning_rate": 2.7000000000000004e-06,
+      "loss": 0.0922,
+      "step": 54
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 0.7521713972091675,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0887,
+      "step": 55
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.7261010408401489,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.0997,
+      "step": 56
+    },
+    {
+      "epoch": 0.49137931034482757,
+      "grad_norm": 0.6530802845954895,
+      "learning_rate": 2.85e-06,
+      "loss": 0.0882,
+      "step": 57
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6899245381355286,
+      "learning_rate": 2.9e-06,
+      "loss": 0.0844,
+      "step": 58
+    },
+    {
+      "epoch": 0.5086206896551724,
+      "grad_norm": 0.6771528124809265,
+      "learning_rate": 2.95e-06,
+      "loss": 0.0884,
+      "step": 59
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.6307985782623291,
+      "learning_rate": 3e-06,
+      "loss": 0.0912,
+      "step": 60
+    },
+    {
+      "epoch": 0.5258620689655172,
+      "grad_norm": 0.5869951844215393,
+      "learning_rate": 3.05e-06,
+      "loss": 0.0875,
+      "step": 61
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 0.6039404273033142,
+      "learning_rate": 3.1000000000000004e-06,
+      "loss": 0.0768,
+      "step": 62
+    },
+    {
+      "epoch": 0.5431034482758621,
+      "grad_norm": 0.49209344387054443,
+      "learning_rate": 3.1500000000000003e-06,
+      "loss": 0.0815,
+      "step": 63
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.7383344769477844,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.0874,
+      "step": 64
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 0.5552617311477661,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0762,
+      "step": 65
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 0.4992441236972809,
+      "learning_rate": 3.3000000000000006e-06,
+      "loss": 0.0793,
+      "step": 66
+    },
+    {
+      "epoch": 0.5775862068965517,
+      "grad_norm": 0.4979636073112488,
+      "learning_rate": 3.3500000000000005e-06,
+      "loss": 0.0792,
+      "step": 67
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.4675934612751007,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.0766,
+      "step": 68
+    },
+    {
+      "epoch": 0.5948275862068966,
+      "grad_norm": 0.49495571851730347,
+      "learning_rate": 3.45e-06,
+      "loss": 0.0824,
+      "step": 69
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.6044315695762634,
+      "learning_rate": 3.5e-06,
+      "loss": 0.0826,
+      "step": 70
+    },
+    {
+      "epoch": 0.6120689655172413,
+      "grad_norm": 0.4898519217967987,
+      "learning_rate": 3.5500000000000003e-06,
+      "loss": 0.0755,
+      "step": 71
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.4218939244747162,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.0762,
+      "step": 72
+    },
+    {
+      "epoch": 0.6293103448275862,
+      "grad_norm": 0.5785802006721497,
+      "learning_rate": 3.65e-06,
+      "loss": 0.0837,
+      "step": 73
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 0.5505399703979492,
+      "learning_rate": 3.7e-06,
+      "loss": 0.0814,
+      "step": 74
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 0.6062561869621277,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.0725,
+      "step": 75
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.707350492477417,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.0913,
+      "step": 76
+    },
+    {
+      "epoch": 0.6637931034482759,
+      "grad_norm": 0.5091889500617981,
+      "learning_rate": 3.85e-06,
+      "loss": 0.0697,
+      "step": 77
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 0.4801473319530487,
+      "learning_rate": 3.900000000000001e-06,
+      "loss": 0.073,
+      "step": 78
+    },
+    {
+      "epoch": 0.6810344827586207,
+      "grad_norm": 0.462162047624588,
+      "learning_rate": 3.95e-06,
+      "loss": 0.0805,
+      "step": 79
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.463969349861145,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0738,
+      "step": 80
+    },
+    {
+      "epoch": 0.6982758620689655,
+      "grad_norm": 0.3980114161968231,
+      "learning_rate": 4.05e-06,
+      "loss": 0.0742,
+      "step": 81
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 0.3627180755138397,
+      "learning_rate": 4.1e-06,
+      "loss": 0.0683,
+      "step": 82
+    },
+    {
+      "epoch": 0.7155172413793104,
+      "grad_norm": 0.39726322889328003,
+      "learning_rate": 4.15e-06,
+      "loss": 0.0717,
+      "step": 83
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.48898085951805115,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.0676,
+      "step": 84
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 0.6143100261688232,
+      "learning_rate": 4.25e-06,
+      "loss": 0.0708,
+      "step": 85
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 0.5028995275497437,
+      "learning_rate": 4.3e-06,
+      "loss": 0.0713,
+      "step": 86
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.5576066970825195,
+      "learning_rate": 4.350000000000001e-06,
+      "loss": 0.078,
+      "step": 87
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.37101301550865173,
+      "learning_rate": 4.4e-06,
+      "loss": 0.071,
+      "step": 88
+    },
+    {
+      "epoch": 0.7672413793103449,
+      "grad_norm": 0.442694753408432,
+      "learning_rate": 4.450000000000001e-06,
+      "loss": 0.0791,
+      "step": 89
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.48991039395332336,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0681,
+      "step": 90
+    },
+    {
+      "epoch": 0.7844827586206896,
+      "grad_norm": 0.46367791295051575,
+      "learning_rate": 4.5500000000000005e-06,
+      "loss": 0.0701,
+      "step": 91
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.3454825282096863,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.0774,
+      "step": 92
+    },
+    {
+      "epoch": 0.8017241379310345,
+      "grad_norm": 0.35102447867393494,
+      "learning_rate": 4.65e-06,
+      "loss": 0.0659,
+      "step": 93
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 0.3791246712207794,
+      "learning_rate": 4.7e-06,
+      "loss": 0.0727,
+      "step": 94
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.3911365270614624,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0641,
+      "step": 95
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.35395047068595886,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.0735,
+      "step": 96
+    },
+    {
+      "epoch": 0.8362068965517241,
+      "grad_norm": 0.3499661087989807,
+      "learning_rate": 4.85e-06,
+      "loss": 0.0657,
+      "step": 97
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 0.34877678751945496,
+      "learning_rate": 4.9000000000000005e-06,
+      "loss": 0.0701,
+      "step": 98
+    },
+    {
+      "epoch": 0.853448275862069,
+      "grad_norm": 0.36436647176742554,
+      "learning_rate": 4.95e-06,
+      "loss": 0.0758,
+      "step": 99
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.4726298749446869,
+      "learning_rate": 5e-06,
+      "loss": 0.0731,
+      "step": 100
+    },
+    {
+      "epoch": 0.8706896551724138,
+      "grad_norm": 0.31892526149749756,
+      "learning_rate": 4.999965269084342e-06,
+      "loss": 0.0635,
+      "step": 101
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 0.3707881569862366,
+      "learning_rate": 4.999861077302358e-06,
+      "loss": 0.0689,
+      "step": 102
+    },
+    {
+      "epoch": 0.8879310344827587,
+      "grad_norm": 0.3244622051715851,
+      "learning_rate": 4.999687427548989e-06,
+      "loss": 0.0645,
+      "step": 103
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.386982262134552,
+      "learning_rate": 4.999444324649045e-06,
+      "loss": 0.0708,
+      "step": 104
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 0.3552643656730652,
+      "learning_rate": 4.999131775357078e-06,
+      "loss": 0.0766,
+      "step": 105
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 0.3503671884536743,
+      "learning_rate": 4.998749788357184e-06,
+      "loss": 0.0733,
+      "step": 106
+    },
+    {
+      "epoch": 0.9224137931034483,
+      "grad_norm": 0.4907379746437073,
+      "learning_rate": 4.998298374262771e-06,
+      "loss": 0.0721,
+      "step": 107
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.305571585893631,
+      "learning_rate": 4.997777545616258e-06,
+      "loss": 0.0603,
+      "step": 108
+    },
+    {
+      "epoch": 0.9396551724137931,
+      "grad_norm": 0.3188783824443817,
+      "learning_rate": 4.99718731688873e-06,
+      "loss": 0.0574,
+      "step": 109
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.3277616500854492,
+      "learning_rate": 4.996527704479535e-06,
+      "loss": 0.0671,
+      "step": 110
+    },
+    {
+      "epoch": 0.9568965517241379,
+      "grad_norm": 0.38640740513801575,
+      "learning_rate": 4.995798726715826e-06,
+      "loss": 0.0625,
+      "step": 111
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.5463483929634094,
+      "learning_rate": 4.995000403852057e-06,
+      "loss": 0.0718,
+      "step": 112
+    },
+    {
+      "epoch": 0.9741379310344828,
+      "grad_norm": 0.3974014222621918,
+      "learning_rate": 4.994132758069413e-06,
+      "loss": 0.071,
+      "step": 113
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 0.3642785847187042,
+      "learning_rate": 4.993195813475202e-06,
+      "loss": 0.0658,
+      "step": 114
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.3118143677711487,
+      "learning_rate": 4.992189596102179e-06,
+      "loss": 0.0633,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.41573596000671387,
+      "learning_rate": 4.991114133907822e-06,
+      "loss": 0.0662,
+      "step": 116
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 696,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 116,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.5985658846497997e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-116/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81869dce97233c4dee9b25cc565b7dbf695ff949fafca7ec37b34379228fbff
+size 8056

checkpoint-116/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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, exclude_frozen_parameters):
+    """
+    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,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,44 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "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": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}