Clean up large checkpoint folders

checkpoint-1000/README.md

@@ -1,208 +0,0 @@
----
-base_model: zai-org/GLM-OCR
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:zai-org/GLM-OCR
-- llama-factory
-- lora
-- transformers
----
-
-# 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 0.18.1

checkpoint-1000/adapter_config.json

@@ -1,60 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "zai-org/GLM-OCR",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "layers.7.mlp.down_proj",
-    "v_proj",
-    "o_proj",
-    "layers.4.mlp.down_proj",
-    "layers.14.mlp.down_proj",
-    "layers.2.mlp.down_proj",
-    "layers.9.mlp.down_proj",
-    "layers.0.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "layers.15.mlp.down_proj",
-    "layers.11.mlp.down_proj",
-    "k_proj",
-    "layers.8.mlp.down_proj",
-    "q_proj",
-    "gate_up_proj",
-    "layers.10.mlp.down_proj",
-    "layers.6.mlp.down_proj",
-    "layers.13.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.12.mlp.down_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

checkpoint-1000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:056d7c4e66ee5f7186524b84ae123edb8d9b3d059affb137e7c9be01e12faaa6
-size 14970360

checkpoint-1000/chat_template.jinja

@@ -1,140 +0,0 @@
-[gMASK]<sop>
-{%- if tools -%}
-<|system|>
-# Tools
-
-You may call one or more functions to assist with the user query.
-
-You are provided with function signatures within <tools></tools> XML tags:
-<tools>
-{% for tool in tools %}
-{{ tool | tojson(ensure_ascii=False) }}
-{% endfor %}
-</tools>
-
-For each function call, output the function name and arguments within the following XML format:
-<tool_call>{function-name}
-<arg_key>{arg-key-1}</arg_key>
-<arg_value>{arg-value-1}</arg_value>
-<arg_key>{arg-key-2}</arg_key>
-<arg_value>{arg-value-2}</arg_value>
-...
-</tool_call>{%- endif -%}
-{%- macro visible_text(content) -%}
-    {%- if content is string -%}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping -%}
-        {%- for item in content -%}
-            {%- if item is mapping and item.type == 'text' -%}
-                {{- item.text }}
-            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
-                <|begin_of_image|><|image|><|end_of_image|>
-            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
-                <|begin_of_video|><|video|><|end_of_video|>
-            {%- elif item is string -%}
-                {{- item }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{- content }}
-    {%- endif -%}
-{%- endmacro -%}
-{%- set ns = namespace(last_user_index=-1) %}
-{%- for m in messages %}
-    {%- if m.role == 'user' %}
-        {% set ns.last_user_index = loop.index0 -%}
-    {%- endif %}
-{%- endfor %}
-{% for m in messages %}
-{%- if m.role == 'user' -%}<|user|>
-{% if m.content is string %}
-{{ m.content }}
-{%- else %}
-{%- for item in m.content %}
-{% if item.type == 'video' or 'video' in item %}
-<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
-<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
-{{ item.text }}
-{%- endif %}
-{%- endfor %}
-{%- endif %}
-{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
-{%- elif m.role == 'assistant' -%}
-<|assistant|>
-{%- set reasoning_content = '' %}
-{%- set content = visible_text(m.content) %}
-{%- if m.reasoning_content is string %}
-    {%- set reasoning_content = m.reasoning_content %}
-{%- else %}
-    {%- if '</think>' in content %}
-        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-    {%- endif %}
-{%- endif %}
-{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
-{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
-{%- else -%}
-{{ '\n<think></think>' }}
-{%- endif -%}
-{%- if content.strip() -%}
-{{ '\n' + content.strip() }}
-{%- endif -%}
-{% if m.tool_calls %}
-{% for tc in m.tool_calls %}
-{%- if tc.function %}
-    {%- set tc = tc.function %}
-{%- endif %}
-{{ '\n<tool_call>' + tc.name }}
-{% set _args = tc.arguments %}
-{% for k, v in _args.items() %}
-<arg_key>{{ k }}</arg_key>
-<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
-{% endfor %}
-</tool_call>{% endfor %}
-{% endif %}
-{%- elif m.role == 'tool' -%}
-{%- if m.content is string -%}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-    {{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{{- m.content }}
-{{- '\n</tool_response>' }}
-{% elif m.content is iterable and m.content is not mapping %}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-{{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{%- for tr in m.content -%}
-  {%- if tr is mapping and tr.type is defined -%}
-    {%- set t = tr.type | lower -%}
-    {%- if t == 'text' and tr.text is defined -%}
-{{ tr.text }}
-    {%- elif t in ['image', 'image_url'] -%}
-<|begin_of_image|><|image|><|end_of_image|>
-    {%- elif t in ['video', 'video_url'] -%}
-<|begin_of_video|><|video|><|end_of_video|>
-    {%- else -%}
-{{ tr | tojson(ensure_ascii=False) }}
-    {%- endif -%}
-  {%- else -%}
-{{ tr.output if tr.output is defined else tr }}
-  {%- endif -%}
-{%- endfor -%}
-{{- '\n</tool_response>' }}
-{%- else -%}
-<|observation|>{% for tr in m.content %}
-
-<tool_response>
-{{ tr.output if tr.output is defined else tr }}
-</tool_response>{% endfor -%}
-{% endif -%}
-{%- elif m.role == 'system' -%}
-<|system|>
-{{ visible_text(m.content) }}
-{%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-<|assistant|>
-{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
-{%- endif -%}

checkpoint-1000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8b9ad02cd19426f44509c2d6f7880ecf1e9150d4017427ecc5bde6ee31d857e
-size 30048843

checkpoint-1000/processor_config.json

@@ -1,67 +0,0 @@
-{
-  "image_processor": {
-    "data_format": "channels_first",
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessorFast",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "merge_size": 2,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2
-  },
-  "processor_class": "Glm46VProcessor",
-  "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "fps": 2,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessor",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "max_duration": 300,
-    "max_image_size": {
-      "longest_edge": 47040000
-    },
-    "merge_size": 2,
-    "num_frames": 16,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2,
-    "video_processor_type": "Glm46VVideoProcessor"
-  }
-}

checkpoint-1000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7fa704d116d422562d9e7b60d92ee6c632e360f974ebb4d9b13ab8ca72370dc9
-size 14645

checkpoint-1000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2667de399383551030f34f44a608968b310e5b467d472789fda64aaae63f35b
-size 1465

checkpoint-1000/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "backend": "tokenizers",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": [
-    "<|user|>",
-    "<|observation|>"
-  ],
-  "is_local": false,
-  "model_max_length": 655380,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "processor_class": "Glm46VProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend"
-}

checkpoint-1000/trainer_state.json

@@ -1,750 +0,0 @@
-{
-  "best_global_step": 1000,
-  "best_metric": 0.5869289636611938,
-  "best_model_checkpoint": "saves/glm-ocr/lora/sft\\checkpoint-1000",
-  "epoch": 0.11170688114387846,
-  "eval_steps": 500,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0011170688114387846,
-      "grad_norm": 0.48102444410324097,
-      "learning_rate": 3.3507073715562173e-07,
-      "loss": 3.8437419891357423,
-      "step": 10
-    },
-    {
-      "epoch": 0.002234137622877569,
-      "grad_norm": 0.4481109380722046,
-      "learning_rate": 7.073715562174237e-07,
-      "loss": 3.724664306640625,
-      "step": 20
-    },
-    {
-      "epoch": 0.003351206434316354,
-      "grad_norm": 0.5849565863609314,
-      "learning_rate": 1.0796723752792258e-06,
-      "loss": 3.8653076171875,
-      "step": 30
-    },
-    {
-      "epoch": 0.004468275245755138,
-      "grad_norm": 0.551055908203125,
-      "learning_rate": 1.4519731943410277e-06,
-      "loss": 3.7893310546875,
-      "step": 40
-    },
-    {
-      "epoch": 0.005585344057193923,
-      "grad_norm": 0.4711555540561676,
-      "learning_rate": 1.8242740134028297e-06,
-      "loss": 3.7168815612792967,
-      "step": 50
-    },
-    {
-      "epoch": 0.006702412868632708,
-      "grad_norm": 0.5075607299804688,
-      "learning_rate": 2.1965748324646315e-06,
-      "loss": 4.076691055297852,
-      "step": 60
-    },
-    {
-      "epoch": 0.007819481680071492,
-      "grad_norm": 0.6019856929779053,
-      "learning_rate": 2.5688756515264335e-06,
-      "loss": 3.8860614776611326,
-      "step": 70
-    },
-    {
-      "epoch": 0.008936550491510277,
-      "grad_norm": 0.6876104474067688,
-      "learning_rate": 2.9411764705882355e-06,
-      "loss": 4.218365859985352,
-      "step": 80
-    },
-    {
-      "epoch": 0.010053619302949061,
-      "grad_norm": 0.5750532746315002,
-      "learning_rate": 3.3134772896500374e-06,
-      "loss": 3.642471694946289,
-      "step": 90
-    },
-    {
-      "epoch": 0.011170688114387846,
-      "grad_norm": 0.818539023399353,
-      "learning_rate": 3.68577810871184e-06,
-      "loss": 4.050487518310547,
-      "step": 100
-    },
-    {
-      "epoch": 0.012287756925826631,
-      "grad_norm": 0.755294680595398,
-      "learning_rate": 4.058078927773641e-06,
-      "loss": 3.5631179809570312,
-      "step": 110
-    },
-    {
-      "epoch": 0.013404825737265416,
-      "grad_norm": 0.7310027480125427,
-      "learning_rate": 4.430379746835443e-06,
-      "loss": 3.797147750854492,
-      "step": 120
-    },
-    {
-      "epoch": 0.0145218945487042,
-      "grad_norm": 1.1505708694458008,
-      "learning_rate": 4.802680565897245e-06,
-      "loss": 3.3393394470214846,
-      "step": 130
-    },
-    {
-      "epoch": 0.015638963360142984,
-      "grad_norm": 0.678546130657196,
-      "learning_rate": 5.174981384959047e-06,
-      "loss": 3.4663516998291017,
-      "step": 140
-    },
-    {
-      "epoch": 0.01675603217158177,
-      "grad_norm": 0.9242318868637085,
-      "learning_rate": 5.547282204020849e-06,
-      "loss": 3.3068470001220702,
-      "step": 150
-    },
-    {
-      "epoch": 0.017873100983020553,
-      "grad_norm": 0.7933996319770813,
-      "learning_rate": 5.919583023082651e-06,
-      "loss": 3.1448570251464845,
-      "step": 160
-    },
-    {
-      "epoch": 0.01899016979445934,
-      "grad_norm": 0.6925396919250488,
-      "learning_rate": 6.2918838421444525e-06,
-      "loss": 3.0427642822265626,
-      "step": 170
-    },
-    {
-      "epoch": 0.020107238605898123,
-      "grad_norm": 0.7535761594772339,
-      "learning_rate": 6.664184661206255e-06,
-      "loss": 2.6695913314819335,
-      "step": 180
-    },
-    {
-      "epoch": 0.02122430741733691,
-      "grad_norm": 0.9215436577796936,
-      "learning_rate": 7.036485480268057e-06,
-      "loss": 2.5888317108154295,
-      "step": 190
-    },
-    {
-      "epoch": 0.022341376228775692,
-      "grad_norm": 0.6355695128440857,
-      "learning_rate": 7.408786299329859e-06,
-      "loss": 2.4019800186157227,
-      "step": 200
-    },
-    {
-      "epoch": 0.023458445040214475,
-      "grad_norm": 0.5758479833602905,
-      "learning_rate": 7.78108711839166e-06,
-      "loss": 2.206129264831543,
-      "step": 210
-    },
-    {
-      "epoch": 0.024575513851653262,
-      "grad_norm": 0.71275794506073,
-      "learning_rate": 8.153387937453464e-06,
-      "loss": 2.044425392150879,
-      "step": 220
-    },
-    {
-      "epoch": 0.025692582663092045,
-      "grad_norm": 0.645555317401886,
-      "learning_rate": 8.525688756515264e-06,
-      "loss": 1.8326286315917968,
-      "step": 230
-    },
-    {
-      "epoch": 0.02680965147453083,
-      "grad_norm": 0.6201381683349609,
-      "learning_rate": 8.897989575577067e-06,
-      "loss": 1.4345648765563965,
-      "step": 240
-    },
-    {
-      "epoch": 0.027926720285969615,
-      "grad_norm": 0.7337267994880676,
-      "learning_rate": 9.270290394638868e-06,
-      "loss": 1.4471503257751466,
-      "step": 250
-    },
-    {
-      "epoch": 0.0290437890974084,
-      "grad_norm": 0.6749716401100159,
-      "learning_rate": 9.64259121370067e-06,
-      "loss": 1.3793041229248046,
-      "step": 260
-    },
-    {
-      "epoch": 0.030160857908847184,
-      "grad_norm": 0.6602213382720947,
-      "learning_rate": 1.0014892032762473e-05,
-      "loss": 1.165940284729004,
-      "step": 270
-    },
-    {
-      "epoch": 0.03127792672028597,
-      "grad_norm": 0.5162089467048645,
-      "learning_rate": 1.0387192851824275e-05,
-      "loss": 1.1233109474182128,
-      "step": 280
-    },
-    {
-      "epoch": 0.03239499553172476,
-      "grad_norm": 0.5335881114006042,
-      "learning_rate": 1.0759493670886076e-05,
-      "loss": 0.9815191268920899,
-      "step": 290
-    },
-    {
-      "epoch": 0.03351206434316354,
-      "grad_norm": 0.5757505297660828,
-      "learning_rate": 1.113179448994788e-05,
-      "loss": 0.9900471687316894,
-      "step": 300
-    },
-    {
-      "epoch": 0.03462913315460232,
-      "grad_norm": 0.5946531295776367,
-      "learning_rate": 1.150409530900968e-05,
-      "loss": 1.0403575897216797,
-      "step": 310
-    },
-    {
-      "epoch": 0.035746201966041107,
-      "grad_norm": 0.3793157637119293,
-      "learning_rate": 1.1876396128071483e-05,
-      "loss": 1.0242424964904786,
-      "step": 320
-    },
-    {
-      "epoch": 0.03686327077747989,
-      "grad_norm": 0.4137881398200989,
-      "learning_rate": 1.2248696947133284e-05,
-      "loss": 0.96560640335083,
-      "step": 330
-    },
-    {
-      "epoch": 0.03798033958891868,
-      "grad_norm": 0.5132653713226318,
-      "learning_rate": 1.2620997766195086e-05,
-      "loss": 0.9560657501220703,
-      "step": 340
-    },
-    {
-      "epoch": 0.03909740840035746,
-      "grad_norm": 0.38656044006347656,
-      "learning_rate": 1.2993298585256889e-05,
-      "loss": 0.8233488082885743,
-      "step": 350
-    },
-    {
-      "epoch": 0.040214477211796246,
-      "grad_norm": 0.44017505645751953,
-      "learning_rate": 1.336559940431869e-05,
-      "loss": 0.7505381584167481,
-      "step": 360
-    },
-    {
-      "epoch": 0.04133154602323503,
-      "grad_norm": 0.4466555118560791,
-      "learning_rate": 1.3737900223380492e-05,
-      "loss": 1.0000381469726562,
-      "step": 370
-    },
-    {
-      "epoch": 0.04244861483467382,
-      "grad_norm": 0.41909196972846985,
-      "learning_rate": 1.4110201042442295e-05,
-      "loss": 0.7742743492126465,
-      "step": 380
-    },
-    {
-      "epoch": 0.0435656836461126,
-      "grad_norm": 0.5523571968078613,
-      "learning_rate": 1.4482501861504097e-05,
-      "loss": 0.8583847999572753,
-      "step": 390
-    },
-    {
-      "epoch": 0.044682752457551385,
-      "grad_norm": 0.485941082239151,
-      "learning_rate": 1.4854802680565899e-05,
-      "loss": 0.8668153762817383,
-      "step": 400
-    },
-    {
-      "epoch": 0.04579982126899017,
-      "grad_norm": 0.4323127567768097,
-      "learning_rate": 1.5227103499627702e-05,
-      "loss": 0.6831861972808838,
-      "step": 410
-    },
-    {
-      "epoch": 0.04691689008042895,
-      "grad_norm": 0.46461915969848633,
-      "learning_rate": 1.55994043186895e-05,
-      "loss": 0.7986338138580322,
-      "step": 420
-    },
-    {
-      "epoch": 0.04803395889186774,
-      "grad_norm": 0.4394327700138092,
-      "learning_rate": 1.5971705137751303e-05,
-      "loss": 0.7741772651672363,
-      "step": 430
-    },
-    {
-      "epoch": 0.049151027703306524,
-      "grad_norm": 0.5871309041976929,
-      "learning_rate": 1.6344005956813105e-05,
-      "loss": 0.8612316131591797,
-      "step": 440
-    },
-    {
-      "epoch": 0.05026809651474531,
-      "grad_norm": 0.4836363196372986,
-      "learning_rate": 1.6716306775874906e-05,
-      "loss": 0.7080867290496826,
-      "step": 450
-    },
-    {
-      "epoch": 0.05138516532618409,
-      "grad_norm": 0.28715530037879944,
-      "learning_rate": 1.7088607594936708e-05,
-      "loss": 0.7109904289245605,
-      "step": 460
-    },
-    {
-      "epoch": 0.05250223413762288,
-      "grad_norm": 0.39397767186164856,
-      "learning_rate": 1.7460908413998513e-05,
-      "loss": 0.8006397247314453,
-      "step": 470
-    },
-    {
-      "epoch": 0.05361930294906166,
-      "grad_norm": 0.5189089775085449,
-      "learning_rate": 1.7833209233060314e-05,
-      "loss": 0.7726738452911377,
-      "step": 480
-    },
-    {
-      "epoch": 0.054736371760500446,
-      "grad_norm": 0.4590846002101898,
-      "learning_rate": 1.8205510052122116e-05,
-      "loss": 0.876410961151123,
-      "step": 490
-    },
-    {
-      "epoch": 0.05585344057193923,
-      "grad_norm": 0.4410800635814667,
-      "learning_rate": 1.8577810871183918e-05,
-      "loss": 0.8238654136657715,
-      "step": 500
-    },
-    {
-      "epoch": 0.05585344057193923,
-      "eval_loss": 0.7669619917869568,
-      "eval_runtime": 299.9937,
-      "eval_samples_per_second": 6.667,
-      "eval_steps_per_second": 6.667,
-      "step": 500
-    },
-    {
-      "epoch": 0.05697050938337802,
-      "grad_norm": 0.4250514507293701,
-      "learning_rate": 1.895011169024572e-05,
-      "loss": 0.7468394756317138,
-      "step": 510
-    },
-    {
-      "epoch": 0.0580875781948168,
-      "grad_norm": 0.404019832611084,
-      "learning_rate": 1.932241250930752e-05,
-      "loss": 0.6975571155548096,
-      "step": 520
-    },
-    {
-      "epoch": 0.059204647006255585,
-      "grad_norm": 0.46538233757019043,
-      "learning_rate": 1.9694713328369326e-05,
-      "loss": 0.7115833282470703,
-      "step": 530
-    },
-    {
-      "epoch": 0.06032171581769437,
-      "grad_norm": 0.3557272255420685,
-      "learning_rate": 2.0067014147431127e-05,
-      "loss": 0.5501380920410156,
-      "step": 540
-    },
-    {
-      "epoch": 0.06143878462913315,
-      "grad_norm": 0.5543599128723145,
-      "learning_rate": 2.043931496649293e-05,
-      "loss": 0.6966252326965332,
-      "step": 550
-    },
-    {
-      "epoch": 0.06255585344057193,
-      "grad_norm": 0.44497013092041016,
-      "learning_rate": 2.081161578555473e-05,
-      "loss": 0.7662677764892578,
-      "step": 560
-    },
-    {
-      "epoch": 0.06367292225201072,
-      "grad_norm": 0.3379228711128235,
-      "learning_rate": 2.118391660461653e-05,
-      "loss": 0.7440553665161133,
-      "step": 570
-    },
-    {
-      "epoch": 0.06478999106344951,
-      "grad_norm": 0.48714378476142883,
-      "learning_rate": 2.1556217423678333e-05,
-      "loss": 0.7602644920349121,
-      "step": 580
-    },
-    {
-      "epoch": 0.06590705987488829,
-      "grad_norm": 0.679702639579773,
-      "learning_rate": 2.1928518242740135e-05,
-      "loss": 0.7181577682495117,
-      "step": 590
-    },
-    {
-      "epoch": 0.06702412868632708,
-      "grad_norm": 0.39104506373405457,
-      "learning_rate": 2.2300819061801936e-05,
-      "loss": 0.7105781078338623,
-      "step": 600
-    },
-    {
-      "epoch": 0.06814119749776586,
-      "grad_norm": 0.4630368947982788,
-      "learning_rate": 2.2673119880863738e-05,
-      "loss": 0.6304820537567138,
-      "step": 610
-    },
-    {
-      "epoch": 0.06925826630920465,
-      "grad_norm": 0.4952685534954071,
-      "learning_rate": 2.304542069992554e-05,
-      "loss": 0.6775004863739014,
-      "step": 620
-    },
-    {
-      "epoch": 0.07037533512064344,
-      "grad_norm": 0.43499284982681274,
-      "learning_rate": 2.341772151898734e-05,
-      "loss": 0.6789637088775635,
-      "step": 630
-    },
-    {
-      "epoch": 0.07149240393208221,
-      "grad_norm": 0.43694499135017395,
-      "learning_rate": 2.3790022338049146e-05,
-      "loss": 0.7337959289550782,
-      "step": 640
-    },
-    {
-      "epoch": 0.072609472743521,
-      "grad_norm": 0.466741144657135,
-      "learning_rate": 2.4162323157110948e-05,
-      "loss": 0.6883241653442382,
-      "step": 650
-    },
-    {
-      "epoch": 0.07372654155495978,
-      "grad_norm": 0.4000166356563568,
-      "learning_rate": 2.453462397617275e-05,
-      "loss": 0.5951610088348389,
-      "step": 660
-    },
-    {
-      "epoch": 0.07484361036639857,
-      "grad_norm": 0.4480671286582947,
-      "learning_rate": 2.490692479523455e-05,
-      "loss": 0.6803426265716552,
-      "step": 670
-    },
-    {
-      "epoch": 0.07596067917783736,
-      "grad_norm": 0.5096255540847778,
-      "learning_rate": 2.5279225614296352e-05,
-      "loss": 0.768033504486084,
-      "step": 680
-    },
-    {
-      "epoch": 0.07707774798927614,
-      "grad_norm": 0.35100409388542175,
-      "learning_rate": 2.5651526433358154e-05,
-      "loss": 0.6422712326049804,
-      "step": 690
-    },
-    {
-      "epoch": 0.07819481680071493,
-      "grad_norm": 0.6556435227394104,
-      "learning_rate": 2.602382725241996e-05,
-      "loss": 0.7157793521881104,
-      "step": 700
-    },
-    {
-      "epoch": 0.07931188561215372,
-      "grad_norm": 0.491706520318985,
-      "learning_rate": 2.6396128071481757e-05,
-      "loss": 0.6762196540832519,
-      "step": 710
-    },
-    {
-      "epoch": 0.08042895442359249,
-      "grad_norm": 0.6594254970550537,
-      "learning_rate": 2.6768428890543562e-05,
-      "loss": 0.6674414157867432,
-      "step": 720
-    },
-    {
-      "epoch": 0.08154602323503128,
-      "grad_norm": 0.6460888981819153,
-      "learning_rate": 2.714072970960536e-05,
-      "loss": 0.694553804397583,
-      "step": 730
-    },
-    {
-      "epoch": 0.08266309204647006,
-      "grad_norm": 0.5787428617477417,
-      "learning_rate": 2.7513030528667165e-05,
-      "loss": 0.6047438144683838,
-      "step": 740
-    },
-    {
-      "epoch": 0.08378016085790885,
-      "grad_norm": 0.45848217606544495,
-      "learning_rate": 2.7885331347728967e-05,
-      "loss": 0.6772585391998291,
-      "step": 750
-    },
-    {
-      "epoch": 0.08489722966934764,
-      "grad_norm": 0.7840375900268555,
-      "learning_rate": 2.825763216679077e-05,
-      "loss": 0.739193344116211,
-      "step": 760
-    },
-    {
-      "epoch": 0.08601429848078641,
-      "grad_norm": 0.4618059992790222,
-      "learning_rate": 2.862993298585257e-05,
-      "loss": 0.6808958530426026,
-      "step": 770
-    },
-    {
-      "epoch": 0.0871313672922252,
-      "grad_norm": 0.5585341453552246,
-      "learning_rate": 2.9002233804914375e-05,
-      "loss": 0.538333797454834,
-      "step": 780
-    },
-    {
-      "epoch": 0.08824843610366398,
-      "grad_norm": 0.4029307961463928,
-      "learning_rate": 2.9374534623976173e-05,
-      "loss": 0.5539563179016114,
-      "step": 790
-    },
-    {
-      "epoch": 0.08936550491510277,
-      "grad_norm": 0.44015660881996155,
-      "learning_rate": 2.9746835443037974e-05,
-      "loss": 0.6564055919647217,
-      "step": 800
-    },
-    {
-      "epoch": 0.09048257372654156,
-      "grad_norm": 0.6777865886688232,
-      "learning_rate": 3.011913626209978e-05,
-      "loss": 0.7128660678863525,
-      "step": 810
-    },
-    {
-      "epoch": 0.09159964253798034,
-      "grad_norm": 0.44157832860946655,
-      "learning_rate": 3.0491437081161578e-05,
-      "loss": 0.6698537349700928,
-      "step": 820
-    },
-    {
-      "epoch": 0.09271671134941913,
-      "grad_norm": 0.35622161626815796,
-      "learning_rate": 3.0863737900223386e-05,
-      "loss": 0.5174383163452149,
-      "step": 830
-    },
-    {
-      "epoch": 0.0938337801608579,
-      "grad_norm": 0.5499693751335144,
-      "learning_rate": 3.123603871928518e-05,
-      "loss": 0.6464185237884521,
-      "step": 840
-    },
-    {
-      "epoch": 0.09495084897229669,
-      "grad_norm": 0.5076237916946411,
-      "learning_rate": 3.160833953834699e-05,
-      "loss": 0.6798902034759522,
-      "step": 850
-    },
-    {
-      "epoch": 0.09606791778373548,
-      "grad_norm": 0.7141596078872681,
-      "learning_rate": 3.1980640357408784e-05,
-      "loss": 0.5945808410644531,
-      "step": 860
-    },
-    {
-      "epoch": 0.09718498659517426,
-      "grad_norm": 0.6842793822288513,
-      "learning_rate": 3.235294117647059e-05,
-      "loss": 0.5609103679656983,
-      "step": 870
-    },
-    {
-      "epoch": 0.09830205540661305,
-      "grad_norm": 0.7959520816802979,
-      "learning_rate": 3.2725241995532394e-05,
-      "loss": 0.6554427146911621,
-      "step": 880
-    },
-    {
-      "epoch": 0.09941912421805184,
-      "grad_norm": 0.42089518904685974,
-      "learning_rate": 3.3097542814594195e-05,
-      "loss": 0.6683910846710205,
-      "step": 890
-    },
-    {
-      "epoch": 0.10053619302949061,
-      "grad_norm": 0.5932669639587402,
-      "learning_rate": 3.3469843633656e-05,
-      "loss": 0.5621670246124267,
-      "step": 900
-    },
-    {
-      "epoch": 0.1016532618409294,
-      "grad_norm": 0.3308563828468323,
-      "learning_rate": 3.38421444527178e-05,
-      "loss": 0.5763424873352051,
-      "step": 910
-    },
-    {
-      "epoch": 0.10277033065236818,
-      "grad_norm": 0.6204649209976196,
-      "learning_rate": 3.42144452717796e-05,
-      "loss": 0.5881050586700439,
-      "step": 920
-    },
-    {
-      "epoch": 0.10388739946380697,
-      "grad_norm": 0.4800551235675812,
-      "learning_rate": 3.45867460908414e-05,
-      "loss": 0.6053416728973389,
-      "step": 930
-    },
-    {
-      "epoch": 0.10500446827524576,
-      "grad_norm": 0.5851083993911743,
-      "learning_rate": 3.49590469099032e-05,
-      "loss": 0.6674454689025879,
-      "step": 940
-    },
-    {
-      "epoch": 0.10612153708668454,
-      "grad_norm": 0.49788594245910645,
-      "learning_rate": 3.5331347728965005e-05,
-      "loss": 0.7128334522247315,
-      "step": 950
-    },
-    {
-      "epoch": 0.10723860589812333,
-      "grad_norm": 0.5501845479011536,
-      "learning_rate": 3.5703648548026806e-05,
-      "loss": 0.6273306369781494,
-      "step": 960
-    },
-    {
-      "epoch": 0.1083556747095621,
-      "grad_norm": 0.5952850580215454,
-      "learning_rate": 3.607594936708861e-05,
-      "loss": 0.6272556781768799,
-      "step": 970
-    },
-    {
-      "epoch": 0.10947274352100089,
-      "grad_norm": 0.4115196466445923,
-      "learning_rate": 3.644825018615041e-05,
-      "loss": 0.6376024723052979,
-      "step": 980
-    },
-    {
-      "epoch": 0.11058981233243968,
-      "grad_norm": 0.5184608101844788,
-      "learning_rate": 3.682055100521221e-05,
-      "loss": 0.5531879425048828,
-      "step": 990
-    },
-    {
-      "epoch": 0.11170688114387846,
-      "grad_norm": 0.49788329005241394,
-      "learning_rate": 3.719285182427402e-05,
-      "loss": 0.6343930244445801,
-      "step": 1000
-    },
-    {
-      "epoch": 0.11170688114387846,
-      "eval_loss": 0.5869289636611938,
-      "eval_runtime": 304.6877,
-      "eval_samples_per_second": 6.564,
-      "eval_steps_per_second": 6.564,
-      "step": 1000
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 26856,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2.4699638799138816e+16,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-1000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17d0904350ec3cac340f5f4264a7fdac37e5e51f1efd4243975931f79bcdea75
-size 5585

checkpoint-10000/README.md

@@ -1,208 +0,0 @@
----
-base_model: zai-org/GLM-OCR
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:zai-org/GLM-OCR
-- llama-factory
-- lora
-- transformers
----
-
-# 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 0.18.1

checkpoint-10000/adapter_config.json

@@ -1,60 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "zai-org/GLM-OCR",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "layers.7.mlp.down_proj",
-    "v_proj",
-    "o_proj",
-    "layers.4.mlp.down_proj",
-    "layers.14.mlp.down_proj",
-    "layers.2.mlp.down_proj",
-    "layers.9.mlp.down_proj",
-    "layers.0.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "layers.15.mlp.down_proj",
-    "layers.11.mlp.down_proj",
-    "k_proj",
-    "layers.8.mlp.down_proj",
-    "q_proj",
-    "gate_up_proj",
-    "layers.10.mlp.down_proj",
-    "layers.6.mlp.down_proj",
-    "layers.13.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.12.mlp.down_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

checkpoint-10000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:862da1efd5394751b8095be48ab36f24b01a3453a4870cf09da5d4f5e1726e5e
-size 14970360

checkpoint-10000/chat_template.jinja

@@ -1,140 +0,0 @@
-[gMASK]<sop>
-{%- if tools -%}
-<|system|>
-# Tools
-
-You may call one or more functions to assist with the user query.
-
-You are provided with function signatures within <tools></tools> XML tags:
-<tools>
-{% for tool in tools %}
-{{ tool | tojson(ensure_ascii=False) }}
-{% endfor %}
-</tools>
-
-For each function call, output the function name and arguments within the following XML format:
-<tool_call>{function-name}
-<arg_key>{arg-key-1}</arg_key>
-<arg_value>{arg-value-1}</arg_value>
-<arg_key>{arg-key-2}</arg_key>
-<arg_value>{arg-value-2}</arg_value>
-...
-</tool_call>{%- endif -%}
-{%- macro visible_text(content) -%}
-    {%- if content is string -%}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping -%}
-        {%- for item in content -%}
-            {%- if item is mapping and item.type == 'text' -%}
-                {{- item.text }}
-            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
-                <|begin_of_image|><|image|><|end_of_image|>
-            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
-                <|begin_of_video|><|video|><|end_of_video|>
-            {%- elif item is string -%}
-                {{- item }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{- content }}
-    {%- endif -%}
-{%- endmacro -%}
-{%- set ns = namespace(last_user_index=-1) %}
-{%- for m in messages %}
-    {%- if m.role == 'user' %}
-        {% set ns.last_user_index = loop.index0 -%}
-    {%- endif %}
-{%- endfor %}
-{% for m in messages %}
-{%- if m.role == 'user' -%}<|user|>
-{% if m.content is string %}
-{{ m.content }}
-{%- else %}
-{%- for item in m.content %}
-{% if item.type == 'video' or 'video' in item %}
-<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
-<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
-{{ item.text }}
-{%- endif %}
-{%- endfor %}
-{%- endif %}
-{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
-{%- elif m.role == 'assistant' -%}
-<|assistant|>
-{%- set reasoning_content = '' %}
-{%- set content = visible_text(m.content) %}
-{%- if m.reasoning_content is string %}
-    {%- set reasoning_content = m.reasoning_content %}
-{%- else %}
-    {%- if '</think>' in content %}
-        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-    {%- endif %}
-{%- endif %}
-{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
-{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
-{%- else -%}
-{{ '\n<think></think>' }}
-{%- endif -%}
-{%- if content.strip() -%}
-{{ '\n' + content.strip() }}
-{%- endif -%}
-{% if m.tool_calls %}
-{% for tc in m.tool_calls %}
-{%- if tc.function %}
-    {%- set tc = tc.function %}
-{%- endif %}
-{{ '\n<tool_call>' + tc.name }}
-{% set _args = tc.arguments %}
-{% for k, v in _args.items() %}
-<arg_key>{{ k }}</arg_key>
-<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
-{% endfor %}
-</tool_call>{% endfor %}
-{% endif %}
-{%- elif m.role == 'tool' -%}
-{%- if m.content is string -%}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-    {{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{{- m.content }}
-{{- '\n</tool_response>' }}
-{% elif m.content is iterable and m.content is not mapping %}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-{{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{%- for tr in m.content -%}
-  {%- if tr is mapping and tr.type is defined -%}
-    {%- set t = tr.type | lower -%}
-    {%- if t == 'text' and tr.text is defined -%}
-{{ tr.text }}
-    {%- elif t in ['image', 'image_url'] -%}
-<|begin_of_image|><|image|><|end_of_image|>
-    {%- elif t in ['video', 'video_url'] -%}
-<|begin_of_video|><|video|><|end_of_video|>
-    {%- else -%}
-{{ tr | tojson(ensure_ascii=False) }}
-    {%- endif -%}
-  {%- else -%}
-{{ tr.output if tr.output is defined else tr }}
-  {%- endif -%}
-{%- endfor -%}
-{{- '\n</tool_response>' }}
-{%- else -%}
-<|observation|>{% for tr in m.content %}
-
-<tool_response>
-{{ tr.output if tr.output is defined else tr }}
-</tool_response>{% endfor -%}
-{% endif -%}
-{%- elif m.role == 'system' -%}
-<|system|>
-{{ visible_text(m.content) }}
-{%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-<|assistant|>
-{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
-{%- endif -%}

checkpoint-10000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3b6bc47ce7b67deedb5f61cc9a5d7eaace53a3e5fffbf7b8a42dd2d740505c7c
-size 30048843

checkpoint-10000/processor_config.json

@@ -1,67 +0,0 @@
-{
-  "image_processor": {
-    "data_format": "channels_first",
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessorFast",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "merge_size": 2,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2
-  },
-  "processor_class": "Glm46VProcessor",
-  "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "fps": 2,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessor",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "max_duration": 300,
-    "max_image_size": {
-      "longest_edge": 47040000
-    },
-    "merge_size": 2,
-    "num_frames": 16,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2,
-    "video_processor_type": "Glm46VVideoProcessor"
-  }
-}

checkpoint-10000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b60e10b0dc9dece2a6195f650703915ef918b35c6e1e4b98c9949fab379f3f57
-size 14645

checkpoint-10000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ba1cb9fafa0bb4446c2f2f1648a7a51d4afb00ea825616a79cfa421d72f1a958
-size 1465

checkpoint-10000/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "backend": "tokenizers",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": [
-    "<|user|>",
-    "<|observation|>"
-  ],
-  "is_local": false,
-  "model_max_length": 655380,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "processor_class": "Glm46VProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend"
-}

checkpoint-10000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17d0904350ec3cac340f5f4264a7fdac37e5e51f1efd4243975931f79bcdea75
-size 5585

checkpoint-10500/README.md

@@ -1,208 +0,0 @@
----
-base_model: zai-org/GLM-OCR
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:zai-org/GLM-OCR
-- llama-factory
-- lora
-- transformers
----
-
-# 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 0.18.1

checkpoint-10500/adapter_config.json

@@ -1,60 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "zai-org/GLM-OCR",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "layers.7.mlp.down_proj",
-    "v_proj",
-    "o_proj",
-    "layers.4.mlp.down_proj",
-    "layers.14.mlp.down_proj",
-    "layers.2.mlp.down_proj",
-    "layers.9.mlp.down_proj",
-    "layers.0.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "layers.15.mlp.down_proj",
-    "layers.11.mlp.down_proj",
-    "k_proj",
-    "layers.8.mlp.down_proj",
-    "q_proj",
-    "gate_up_proj",
-    "layers.10.mlp.down_proj",
-    "layers.6.mlp.down_proj",
-    "layers.13.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.12.mlp.down_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

checkpoint-10500/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4a8567ebe276187ce27f86b5cf2ef8c719d5130e8c2d8d03ab9f5badfad326db
-size 14970360

checkpoint-10500/chat_template.jinja

@@ -1,140 +0,0 @@
-[gMASK]<sop>
-{%- if tools -%}
-<|system|>
-# Tools
-
-You may call one or more functions to assist with the user query.
-
-You are provided with function signatures within <tools></tools> XML tags:
-<tools>
-{% for tool in tools %}
-{{ tool | tojson(ensure_ascii=False) }}
-{% endfor %}
-</tools>
-
-For each function call, output the function name and arguments within the following XML format:
-<tool_call>{function-name}
-<arg_key>{arg-key-1}</arg_key>
-<arg_value>{arg-value-1}</arg_value>
-<arg_key>{arg-key-2}</arg_key>
-<arg_value>{arg-value-2}</arg_value>
-...
-</tool_call>{%- endif -%}
-{%- macro visible_text(content) -%}
-    {%- if content is string -%}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping -%}
-        {%- for item in content -%}
-            {%- if item is mapping and item.type == 'text' -%}
-                {{- item.text }}
-            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
-                <|begin_of_image|><|image|><|end_of_image|>
-            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
-                <|begin_of_video|><|video|><|end_of_video|>
-            {%- elif item is string -%}
-                {{- item }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{- content }}
-    {%- endif -%}
-{%- endmacro -%}
-{%- set ns = namespace(last_user_index=-1) %}
-{%- for m in messages %}
-    {%- if m.role == 'user' %}
-        {% set ns.last_user_index = loop.index0 -%}
-    {%- endif %}
-{%- endfor %}
-{% for m in messages %}
-{%- if m.role == 'user' -%}<|user|>
-{% if m.content is string %}
-{{ m.content }}
-{%- else %}
-{%- for item in m.content %}
-{% if item.type == 'video' or 'video' in item %}
-<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
-<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
-{{ item.text }}
-{%- endif %}
-{%- endfor %}
-{%- endif %}
-{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
-{%- elif m.role == 'assistant' -%}
-<|assistant|>
-{%- set reasoning_content = '' %}
-{%- set content = visible_text(m.content) %}
-{%- if m.reasoning_content is string %}
-    {%- set reasoning_content = m.reasoning_content %}
-{%- else %}
-    {%- if '</think>' in content %}
-        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-    {%- endif %}
-{%- endif %}
-{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
-{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
-{%- else -%}
-{{ '\n<think></think>' }}
-{%- endif -%}
-{%- if content.strip() -%}
-{{ '\n' + content.strip() }}
-{%- endif -%}
-{% if m.tool_calls %}
-{% for tc in m.tool_calls %}
-{%- if tc.function %}
-    {%- set tc = tc.function %}
-{%- endif %}
-{{ '\n<tool_call>' + tc.name }}
-{% set _args = tc.arguments %}
-{% for k, v in _args.items() %}
-<arg_key>{{ k }}</arg_key>
-<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
-{% endfor %}
-</tool_call>{% endfor %}
-{% endif %}
-{%- elif m.role == 'tool' -%}
-{%- if m.content is string -%}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-    {{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{{- m.content }}
-{{- '\n</tool_response>' }}
-{% elif m.content is iterable and m.content is not mapping %}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-{{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{%- for tr in m.content -%}
-  {%- if tr is mapping and tr.type is defined -%}
-    {%- set t = tr.type | lower -%}
-    {%- if t == 'text' and tr.text is defined -%}
-{{ tr.text }}
-    {%- elif t in ['image', 'image_url'] -%}
-<|begin_of_image|><|image|><|end_of_image|>
-    {%- elif t in ['video', 'video_url'] -%}
-<|begin_of_video|><|video|><|end_of_video|>
-    {%- else -%}
-{{ tr | tojson(ensure_ascii=False) }}
-    {%- endif -%}
-  {%- else -%}
-{{ tr.output if tr.output is defined else tr }}
-  {%- endif -%}
-{%- endfor -%}
-{{- '\n</tool_response>' }}
-{%- else -%}
-<|observation|>{% for tr in m.content %}
-
-<tool_response>
-{{ tr.output if tr.output is defined else tr }}
-</tool_response>{% endfor -%}
-{% endif -%}
-{%- elif m.role == 'system' -%}
-<|system|>
-{{ visible_text(m.content) }}
-{%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-<|assistant|>
-{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
-{%- endif -%}

checkpoint-10500/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:196f6ff422f8ca5aff45300c85d5d23b4e4ff4464e335c13f6a4578a1d67178a
-size 30048843

checkpoint-10500/processor_config.json

@@ -1,67 +0,0 @@
-{
-  "image_processor": {
-    "data_format": "channels_first",
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessorFast",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "merge_size": 2,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2
-  },
-  "processor_class": "Glm46VProcessor",
-  "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "fps": 2,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessor",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "max_duration": 300,
-    "max_image_size": {
-      "longest_edge": 47040000
-    },
-    "merge_size": 2,
-    "num_frames": 16,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2,
-    "video_processor_type": "Glm46VVideoProcessor"
-  }
-}

checkpoint-10500/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:662943d9c82c1f1c234827888b51ee6b3db6fec274250e443dfe6cddc82d188f
-size 14645

checkpoint-10500/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b26274f4f828d6e1ee751fc9ad143ce7e3070cf0f85425c714f0b72bd935cf1a
-size 1465

checkpoint-10500/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "backend": "tokenizers",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": [
-    "<|user|>",
-    "<|observation|>"
-  ],
-  "is_local": false,
-  "model_max_length": 655380,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "processor_class": "Glm46VProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend"
-}

checkpoint-10500/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17d0904350ec3cac340f5f4264a7fdac37e5e51f1efd4243975931f79bcdea75
-size 5585

checkpoint-11000/README.md

@@ -1,208 +0,0 @@
----
-base_model: zai-org/GLM-OCR
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:zai-org/GLM-OCR
-- llama-factory
-- lora
-- transformers
----
-
-# 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 0.18.1

checkpoint-11000/adapter_config.json

@@ -1,60 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "zai-org/GLM-OCR",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "layers.7.mlp.down_proj",
-    "v_proj",
-    "o_proj",
-    "layers.4.mlp.down_proj",
-    "layers.14.mlp.down_proj",
-    "layers.2.mlp.down_proj",
-    "layers.9.mlp.down_proj",
-    "layers.0.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "layers.15.mlp.down_proj",
-    "layers.11.mlp.down_proj",
-    "k_proj",
-    "layers.8.mlp.down_proj",
-    "q_proj",
-    "gate_up_proj",
-    "layers.10.mlp.down_proj",
-    "layers.6.mlp.down_proj",
-    "layers.13.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.12.mlp.down_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}

checkpoint-11000/adapter_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fb49b054422370c54bf7cb74056c6f030da9669fd885c6d4aaf1dd1a184adadc
-size 14970360

checkpoint-11000/chat_template.jinja

@@ -1,140 +0,0 @@
-[gMASK]<sop>
-{%- if tools -%}
-<|system|>
-# Tools
-
-You may call one or more functions to assist with the user query.
-
-You are provided with function signatures within <tools></tools> XML tags:
-<tools>
-{% for tool in tools %}
-{{ tool | tojson(ensure_ascii=False) }}
-{% endfor %}
-</tools>
-
-For each function call, output the function name and arguments within the following XML format:
-<tool_call>{function-name}
-<arg_key>{arg-key-1}</arg_key>
-<arg_value>{arg-value-1}</arg_value>
-<arg_key>{arg-key-2}</arg_key>
-<arg_value>{arg-value-2}</arg_value>
-...
-</tool_call>{%- endif -%}
-{%- macro visible_text(content) -%}
-    {%- if content is string -%}
-        {{- content }}
-    {%- elif content is iterable and content is not mapping -%}
-        {%- for item in content -%}
-            {%- if item is mapping and item.type == 'text' -%}
-                {{- item.text }}
-            {%- elif item is mapping and (item.type == 'image' or 'image' in item) -%}
-                <|begin_of_image|><|image|><|end_of_image|>
-            {%- elif item is mapping and (item.type == 'video' or 'video' in item) -%}
-                <|begin_of_video|><|video|><|end_of_video|>
-            {%- elif item is string -%}
-                {{- item }}
-            {%- endif -%}
-        {%- endfor -%}
-    {%- else -%}
-        {{- content }}
-    {%- endif -%}
-{%- endmacro -%}
-{%- set ns = namespace(last_user_index=-1) %}
-{%- for m in messages %}
-    {%- if m.role == 'user' %}
-        {% set ns.last_user_index = loop.index0 -%}
-    {%- endif %}
-{%- endfor %}
-{% for m in messages %}
-{%- if m.role == 'user' -%}<|user|>
-{% if m.content is string %}
-{{ m.content }}
-{%- else %}
-{%- for item in m.content %}
-{% if item.type == 'video' or 'video' in item %}
-<|begin_of_video|><|video|><|end_of_video|>{% elif item.type == 'image' or 'image' in item %}
-<|begin_of_image|><|image|><|end_of_image|>{% elif item.type == 'text' %}
-{{ item.text }}
-{%- endif %}
-{%- endfor %}
-{%- endif %}
-{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
-{%- elif m.role == 'assistant' -%}
-<|assistant|>
-{%- set reasoning_content = '' %}
-{%- set content = visible_text(m.content) %}
-{%- if m.reasoning_content is string %}
-    {%- set reasoning_content = m.reasoning_content %}
-{%- else %}
-    {%- if '</think>' in content %}
-        {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
-        {%- set content = content.split('</think>')[-1].lstrip('\n') %}
-    {%- endif %}
-{%- endif %}
-{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
-{{ '\n<think>' + reasoning_content.strip() +  '</think>'}}
-{%- else -%}
-{{ '\n<think></think>' }}
-{%- endif -%}
-{%- if content.strip() -%}
-{{ '\n' + content.strip() }}
-{%- endif -%}
-{% if m.tool_calls %}
-{% for tc in m.tool_calls %}
-{%- if tc.function %}
-    {%- set tc = tc.function %}
-{%- endif %}
-{{ '\n<tool_call>' + tc.name }}
-{% set _args = tc.arguments %}
-{% for k, v in _args.items() %}
-<arg_key>{{ k }}</arg_key>
-<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
-{% endfor %}
-</tool_call>{% endfor %}
-{% endif %}
-{%- elif m.role == 'tool' -%}
-{%- if m.content is string -%}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-    {{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{{- m.content }}
-{{- '\n</tool_response>' }}
-{% elif m.content is iterable and m.content is not mapping %}
-{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
-{{- '<|observation|>' }}
-{%- endif %}
-{{- '\n<tool_response>\n' }}
-{%- for tr in m.content -%}
-  {%- if tr is mapping and tr.type is defined -%}
-    {%- set t = tr.type | lower -%}
-    {%- if t == 'text' and tr.text is defined -%}
-{{ tr.text }}
-    {%- elif t in ['image', 'image_url'] -%}
-<|begin_of_image|><|image|><|end_of_image|>
-    {%- elif t in ['video', 'video_url'] -%}
-<|begin_of_video|><|video|><|end_of_video|>
-    {%- else -%}
-{{ tr | tojson(ensure_ascii=False) }}
-    {%- endif -%}
-  {%- else -%}
-{{ tr.output if tr.output is defined else tr }}
-  {%- endif -%}
-{%- endfor -%}
-{{- '\n</tool_response>' }}
-{%- else -%}
-<|observation|>{% for tr in m.content %}
-
-<tool_response>
-{{ tr.output if tr.output is defined else tr }}
-</tool_response>{% endfor -%}
-{% endif -%}
-{%- elif m.role == 'system' -%}
-<|system|>
-{{ visible_text(m.content) }}
-{%- endif -%}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-<|assistant|>
-{{'<think></think>\n' if (enable_thinking is defined and not enable_thinking) else ''}}
-{%- endif -%}

checkpoint-11000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:62c6ebd836409ffb1454970ccaf78bfdb91c8efd65d9dc81dbaafa3ed0d40372
-size 30048843

checkpoint-11000/processor_config.json

@@ -1,67 +0,0 @@
-{
-  "image_processor": {
-    "data_format": "channels_first",
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessorFast",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "merge_size": 2,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2
-  },
-  "processor_class": "Glm46VProcessor",
-  "video_processor": {
-    "data_format": "channels_first",
-    "default_to_square": true,
-    "do_convert_rgb": true,
-    "do_normalize": true,
-    "do_rescale": true,
-    "do_resize": true,
-    "do_sample_frames": true,
-    "fps": 2,
-    "image_mean": [
-      0.48145466,
-      0.4578275,
-      0.40821073
-    ],
-    "image_processor_type": "Glm46VImageProcessor",
-    "image_std": [
-      0.26862954,
-      0.26130258,
-      0.27577711
-    ],
-    "max_duration": 300,
-    "max_image_size": {
-      "longest_edge": 47040000
-    },
-    "merge_size": 2,
-    "num_frames": 16,
-    "patch_size": 14,
-    "resample": 3,
-    "rescale_factor": 0.00392156862745098,
-    "return_metadata": false,
-    "size": {
-      "longest_edge": 9633792,
-      "shortest_edge": 12544
-    },
-    "temporal_patch_size": 2,
-    "video_processor_type": "Glm46VVideoProcessor"
-  }
-}

checkpoint-11000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:40f5d49578e8e2171d4202c8698857333d801dfb6992d04a10d925a004520c42
-size 14645

checkpoint-11000/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ad0f08e8ec8f6286ea7a4b3429575804a33c13b61922c784d6742a2a4b5a4edb
-size 1465

checkpoint-11000/tokenizer_config.json

@@ -1,16 +0,0 @@
-{
-  "backend": "tokenizers",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|endoftext|>",
-  "extra_special_tokens": [
-    "<|user|>",
-    "<|observation|>"
-  ],
-  "is_local": false,
-  "model_max_length": 655380,
-  "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "processor_class": "Glm46VProcessor",
-  "split_special_tokens": false,
-  "tokenizer_class": "TokenizersBackend"
-}

checkpoint-11000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:17d0904350ec3cac340f5f4264a7fdac37e5e51f1efd4243975931f79bcdea75
-size 5585

checkpoint-11500/README.md

@@ -1,208 +0,0 @@
----
-base_model: zai-org/GLM-OCR
-library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:zai-org/GLM-OCR
-- llama-factory
-- lora
-- transformers
----
-
-# 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 0.18.1

checkpoint-11500/adapter_config.json

@@ -1,60 +0,0 @@
-{
-  "alora_invocation_tokens": null,
-  "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": null,
-  "base_model_name_or_path": "zai-org/GLM-OCR",
-  "bias": "none",
-  "corda_config": null,
-  "ensure_weight_tying": false,
-  "eva_config": null,
-  "exclude_modules": null,
-  "fan_in_fan_out": false,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_bias": false,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "layers.7.mlp.down_proj",
-    "v_proj",
-    "o_proj",
-    "layers.4.mlp.down_proj",
-    "layers.14.mlp.down_proj",
-    "layers.2.mlp.down_proj",
-    "layers.9.mlp.down_proj",
-    "layers.0.mlp.down_proj",
-    "layers.3.mlp.down_proj",
-    "layers.15.mlp.down_proj",
-    "layers.11.mlp.down_proj",
-    "k_proj",
-    "layers.8.mlp.down_proj",
-    "q_proj",
-    "gate_up_proj",
-    "layers.10.mlp.down_proj",
-    "layers.6.mlp.down_proj",
-    "layers.13.mlp.down_proj",
-    "layers.1.mlp.down_proj",
-    "layers.5.mlp.down_proj",
-    "layers.12.mlp.down_proj"
-  ],
-  "target_parameters": null,
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_qalora": false,
-  "use_rslora": false
-}