sft adapter bl_63cd1bf7_smokefull

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 bl_a0ccbcff_smoke600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 bl_a0ccbcff_smokefull/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+bl_63cd1bf7_smokefull/tokenizer.json filter=lfs diff=lfs merge=lfs -text

bl_63cd1bf7_smokefull/README.md

@@ -0,0 +1,207 @@
+---
+base_model: models/base_resized
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:models/base_resized
+- 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 0.19.1

bl_63cd1bf7_smokefull/adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/base_resized",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

bl_63cd1bf7_smokefull/adapter_manifest.json

@@ -0,0 +1,58 @@
+{
+  "adapter_sha256": "682c8139dcbc0170c72b3f3d6ed39d5110268403861013c93922a23854d77b34",
+  "adapter_step": 162,
+  "base_model_id": "Qwen/Qwen2.5-VL-3B-Instruct",
+  "levers": {
+    "max_pixels": 200704,
+    "max_seq_len": 1024,
+    "min_pixels": 3136
+  },
+  "lora": {
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "lora_r": 16,
+    "lora_target_modules": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  },
+  "optim": {
+    "effective_batch_size": 32,
+    "epochs": 2,
+    "gradient_accumulation_steps": 32,
+    "gradient_checkpointing": true,
+    "learning_rate_lora": 0.0003,
+    "max_grad_norm": 1.0,
+    "per_device_batch_size": 1,
+    "scheduler": "cosine",
+    "seed": 0,
+    "warmup_ratio": 0.03
+  },
+  "quantization": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "load_in_4bit": true
+  },
+  "run_id": "bl_63cd1bf7",
+  "stage": "sft_qlora",
+  "tied_embedding_status": "tied",
+  "tokenizer_version": "vq_v2_srgbres_17to4_cb256_t64__w91cffdd2c82f",
+  "train_report": {
+    "epochs": 2,
+    "mean_loss": 1.7471296659492555,
+    "rows": 2864,
+    "rows_trained": 5184,
+    "seed": 0,
+    "skipped": 544,
+    "smoke_size": null,
+    "steps": 162
+  },
+  "vocab_size_after_resize": 151924,
+  "vq_codebook_sha256": "bcdf369dd7cd9a99d71f240b0dac67d404f52130dc8c35d14d6a04514349d118"
+}

bl_63cd1bf7_smokefull/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b70a1316326887115447e926f14b2ba34a387c0ef74f5cba43d14ddfecd22c
+size 2637838160

bl_63cd1bf7_smokefull/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

bl_63cd1bf7_smokefull/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81301c7f56e6e0a645ce03af82d70c0dae70b903aa38b89f01656097ccb2e528
+size 11470070

bl_63cd1bf7_smokefull/tokenizer_config.json

@@ -0,0 +1,279 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<lut_bos>",
+    "<lut_eos>",
+    "<unsupported>",
+    "<lut_000>",
+    "<lut_001>",
+    "<lut_002>",
+    "<lut_003>",
+    "<lut_004>",
+    "<lut_005>",
+    "<lut_006>",
+    "<lut_007>",
+    "<lut_008>",
+    "<lut_009>",
+    "<lut_010>",
+    "<lut_011>",
+    "<lut_012>",
+    "<lut_013>",
+    "<lut_014>",
+    "<lut_015>",
+    "<lut_016>",
+    "<lut_017>",
+    "<lut_018>",
+    "<lut_019>",
+    "<lut_020>",
+    "<lut_021>",
+    "<lut_022>",
+    "<lut_023>",
+    "<lut_024>",
+    "<lut_025>",
+    "<lut_026>",
+    "<lut_027>",
+    "<lut_028>",
+    "<lut_029>",
+    "<lut_030>",
+    "<lut_031>",
+    "<lut_032>",
+    "<lut_033>",
+    "<lut_034>",
+    "<lut_035>",
+    "<lut_036>",
+    "<lut_037>",
+    "<lut_038>",
+    "<lut_039>",
+    "<lut_040>",
+    "<lut_041>",
+    "<lut_042>",
+    "<lut_043>",
+    "<lut_044>",
+    "<lut_045>",
+    "<lut_046>",
+    "<lut_047>",
+    "<lut_048>",
+    "<lut_049>",
+    "<lut_050>",
+    "<lut_051>",
+    "<lut_052>",
+    "<lut_053>",
+    "<lut_054>",
+    "<lut_055>",
+    "<lut_056>",
+    "<lut_057>",
+    "<lut_058>",
+    "<lut_059>",
+    "<lut_060>",
+    "<lut_061>",
+    "<lut_062>",
+    "<lut_063>",
+    "<lut_064>",
+    "<lut_065>",
+    "<lut_066>",
+    "<lut_067>",
+    "<lut_068>",
+    "<lut_069>",
+    "<lut_070>",
+    "<lut_071>",
+    "<lut_072>",
+    "<lut_073>",
+    "<lut_074>",
+    "<lut_075>",
+    "<lut_076>",
+    "<lut_077>",
+    "<lut_078>",
+    "<lut_079>",
+    "<lut_080>",
+    "<lut_081>",
+    "<lut_082>",
+    "<lut_083>",
+    "<lut_084>",
+    "<lut_085>",
+    "<lut_086>",
+    "<lut_087>",
+    "<lut_088>",
+    "<lut_089>",
+    "<lut_090>",
+    "<lut_091>",
+    "<lut_092>",
+    "<lut_093>",
+    "<lut_094>",
+    "<lut_095>",
+    "<lut_096>",
+    "<lut_097>",
+    "<lut_098>",
+    "<lut_099>",
+    "<lut_100>",
+    "<lut_101>",
+    "<lut_102>",
+    "<lut_103>",
+    "<lut_104>",
+    "<lut_105>",
+    "<lut_106>",
+    "<lut_107>",
+    "<lut_108>",
+    "<lut_109>",
+    "<lut_110>",
+    "<lut_111>",
+    "<lut_112>",
+    "<lut_113>",
+    "<lut_114>",
+    "<lut_115>",
+    "<lut_116>",
+    "<lut_117>",
+    "<lut_118>",
+    "<lut_119>",
+    "<lut_120>",
+    "<lut_121>",
+    "<lut_122>",
+    "<lut_123>",
+    "<lut_124>",
+    "<lut_125>",
+    "<lut_126>",
+    "<lut_127>",
+    "<lut_128>",
+    "<lut_129>",
+    "<lut_130>",
+    "<lut_131>",
+    "<lut_132>",
+    "<lut_133>",
+    "<lut_134>",
+    "<lut_135>",
+    "<lut_136>",
+    "<lut_137>",
+    "<lut_138>",
+    "<lut_139>",
+    "<lut_140>",
+    "<lut_141>",
+    "<lut_142>",
+    "<lut_143>",
+    "<lut_144>",
+    "<lut_145>",
+    "<lut_146>",
+    "<lut_147>",
+    "<lut_148>",
+    "<lut_149>",
+    "<lut_150>",
+    "<lut_151>",
+    "<lut_152>",
+    "<lut_153>",
+    "<lut_154>",
+    "<lut_155>",
+    "<lut_156>",
+    "<lut_157>",
+    "<lut_158>",
+    "<lut_159>",
+    "<lut_160>",
+    "<lut_161>",
+    "<lut_162>",
+    "<lut_163>",
+    "<lut_164>",
+    "<lut_165>",
+    "<lut_166>",
+    "<lut_167>",
+    "<lut_168>",
+    "<lut_169>",
+    "<lut_170>",
+    "<lut_171>",
+    "<lut_172>",
+    "<lut_173>",
+    "<lut_174>",
+    "<lut_175>",
+    "<lut_176>",
+    "<lut_177>",
+    "<lut_178>",
+    "<lut_179>",
+    "<lut_180>",
+    "<lut_181>",
+    "<lut_182>",
+    "<lut_183>",
+    "<lut_184>",
+    "<lut_185>",
+    "<lut_186>",
+    "<lut_187>",
+    "<lut_188>",
+    "<lut_189>",
+    "<lut_190>",
+    "<lut_191>",
+    "<lut_192>",
+    "<lut_193>",
+    "<lut_194>",
+    "<lut_195>",
+    "<lut_196>",
+    "<lut_197>",
+    "<lut_198>",
+    "<lut_199>",
+    "<lut_200>",
+    "<lut_201>",
+    "<lut_202>",
+    "<lut_203>",
+    "<lut_204>",
+    "<lut_205>",
+    "<lut_206>",
+    "<lut_207>",
+    "<lut_208>",
+    "<lut_209>",
+    "<lut_210>",
+    "<lut_211>",
+    "<lut_212>",
+    "<lut_213>",
+    "<lut_214>",
+    "<lut_215>",
+    "<lut_216>",
+    "<lut_217>",
+    "<lut_218>",
+    "<lut_219>",
+    "<lut_220>",
+    "<lut_221>",
+    "<lut_222>",
+    "<lut_223>",
+    "<lut_224>",
+    "<lut_225>",
+    "<lut_226>",
+    "<lut_227>",
+    "<lut_228>",
+    "<lut_229>",
+    "<lut_230>",
+    "<lut_231>",
+    "<lut_232>",
+    "<lut_233>",
+    "<lut_234>",
+    "<lut_235>",
+    "<lut_236>",
+    "<lut_237>",
+    "<lut_238>",
+    "<lut_239>",
+    "<lut_240>",
+    "<lut_241>",
+    "<lut_242>",
+    "<lut_243>",
+    "<lut_244>",
+    "<lut_245>",
+    "<lut_246>",
+    "<lut_247>",
+    "<lut_248>",
+    "<lut_249>",
+    "<lut_250>",
+    "<lut_251>",
+    "<lut_252>",
+    "<lut_253>",
+    "<lut_254>",
+    "<lut_255>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "max_pixels": 200704,
+  "min_pixels": 3136,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}