Upload folder using huggingface_hub (part 4)

checkpoint-80/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6b1177b8ca8dbf34bd6fd18a209180b9227c0cf77d461fbd7e0b9f9c95a3f5
+size 16389

checkpoint-80/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adc9a8b3dd0672048a55e956ef3c6c8a2178a4b454656c51af89b2cef258c01
+size 16389

checkpoint-80/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b699180989ac2f292f3f75c343c07702e28771ea0fd791bd5d83bc45c244938e
+size 16389

checkpoint-80/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab90162c14dfb0bd58c218edc0c0e591e8650193664e19c780b9602d9f07e95a
+size 16389

checkpoint-80/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f98a4e76b0787562ebac45d5f59570f9d35455edeb67046ee33684076cc0b9
+size 16389

checkpoint-80/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855c5ec04e2add9a2ec37fe4c15cf2455a0d4ff6599359be5099580756d589f2
+size 1465

checkpoint-80/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

checkpoint-80/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

checkpoint-80/trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2698412698412698,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.25798711776733396,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 0.6395628452301025,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.33170533180236816,
+      "mean_token_accuracy": 0.9083019256591797,
+      "num_tokens": 2249744.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.1518770933151245,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 0.27742329239845276,
+      "learning_rate": 4.9966852247120764e-05,
+      "loss": 0.14515713453292847,
+      "mean_token_accuracy": 0.9476617932319641,
+      "num_tokens": 4502357.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.1205204889178276,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.15280286967754364,
+      "learning_rate": 4.976460088644493e-05,
+      "loss": 0.11978392601013184,
+      "mean_token_accuracy": 0.9552689790725708,
+      "num_tokens": 6750630.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.1094709500670433,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 0.13621626794338226,
+      "learning_rate": 4.938000100611456e-05,
+      "loss": 0.10746543407440186,
+      "mean_token_accuracy": 0.9598726153373718,
+      "num_tokens": 8991471.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.10419090241193771,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 0.16320250928401947,
+      "learning_rate": 4.881588452008456e-05,
+      "loss": 0.10661067962646484,
+      "mean_token_accuracy": 0.9599695205688477,
+      "num_tokens": 11228489.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.09569432139396668,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.15873780846595764,
+      "learning_rate": 4.80764051721044e-05,
+      "loss": 0.09594419002532958,
+      "mean_token_accuracy": 0.9637031435966492,
+      "num_tokens": 13464387.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.09625398516654968,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.15297284722328186,
+      "learning_rate": 4.7167007950568505e-05,
+      "loss": 0.09495124220848083,
+      "mean_token_accuracy": 0.964220929145813,
+      "num_tokens": 15709681.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.09195081293582916,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 0.15219081938266754,
+      "learning_rate": 4.609438899557964e-05,
+      "loss": 0.09150891304016114,
+      "mean_token_accuracy": 0.9652478575706482,
+      "num_tokens": 17987403.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.08980809897184372,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.1412411779165268,
+      "learning_rate": 4.4866446293440626e-05,
+      "loss": 0.0898817539215088,
+      "mean_token_accuracy": 0.965602707862854,
+      "num_tokens": 20231746.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.08743101209402085,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 0.16695629060268402,
+      "learning_rate": 4.3492221521624174e-05,
+      "loss": 0.08715485334396363,
+      "mean_token_accuracy": 0.9668790459632873,
+      "num_tokens": 22491762.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.08765677958726883,
+      "epoch": 0.873015873015873,
+      "grad_norm": 0.21143023669719696,
+      "learning_rate": 4.198183347243233e-05,
+      "loss": 0.08766236305236816,
+      "mean_token_accuracy": 0.9668452143669128,
+      "num_tokens": 24752715.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.08127444982528687,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.18779045343399048,
+      "learning_rate": 4.03464035455653e-05,
+      "loss": 0.08236484527587891,
+      "mean_token_accuracy": 0.9689654350280762,
+      "num_tokens": 26982538.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.07894417196512223,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 0.1385810822248459,
+      "learning_rate": 3.859797385821812e-05,
+      "loss": 0.0778856873512268,
+      "mean_token_accuracy": 0.9699163198471069,
+      "num_tokens": 29221704.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.07985353171825409,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.16439372301101685,
+      "learning_rate": 3.6749418575683e-05,
+      "loss": 0.07885851860046386,
+      "mean_token_accuracy": 0.969633674621582,
+      "num_tokens": 31470338.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.07194689065217971,
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.16862133145332336,
+      "learning_rate": 3.48143491153543e-05,
+      "loss": 0.074225252866745,
+      "mean_token_accuracy": 0.9716025114059448,
+      "num_tokens": 33719303.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.07757648378610611,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 0.14261098206043243,
+      "learning_rate": 3.280701392214487e-05,
+      "loss": 0.07595503330230713,
+      "mean_token_accuracy": 0.9707554697990417,
+      "num_tokens": 35977913.0,
+      "step": 80
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 8,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0051969670884884e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63584b641880ca8f7031099a802ca6e2de6c8e3fdacc7cdffeaa3f69e77b5a9a
+size 5969

checkpoint-88/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3.5-9B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-9B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.20.0

checkpoint-88/adapter_config.json

@@ -0,0 +1,55 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-9B",
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "in_proj_a",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj",
+    "down_proj",
+    "in_proj_b",
+    "q_proj",
+    "out_proj",
+    "in_proj_qkv",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-88/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37cbb486508a6dee878185dc49a6b8e5ae816602c6548da9c7134a30b273bd60
+size 1384975816

checkpoint-88/chat_template.jinja

@@ -0,0 +1,20 @@
+{%- if messages and messages[0].role == 'system' %}
+{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+{%- set loop_messages = messages[1:] %}
+{%- else %}
+{%- set loop_messages = messages %}
+{%- endif %}
+{%- for message in loop_messages %}
+{{- '<|im_start|>' + message.role + '\n' }}
+{%- if message.role == 'assistant' %}
+{% generation %}{{- message.content + '<|im_end|>' }}{% endgeneration %}{{- '\n' }}
+{%- else %}
+{{- message.content + '<|im_end|>\n' }}
+{%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+{{- '<|im_start|>assistant\n' }}
+{%- if enable_thinking is not defined or not enable_thinking %}
+{{- '<think>\n\n</think>\n\n' }}
+{%- endif %}
+{%- endif %}

checkpoint-88/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf34f1220cb78911cebc9022229e7c77b507e2888e1454030846c66f55f2dc2
+size 2770239667

checkpoint-88/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9ae0f631520c88bdb2a6afd38958318a15b74b5a686f55b5a8460a1dbd25958
+size 16389

checkpoint-88/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b958c6e3c89f080e73b52e8625f7f18d29f1dd38b9fe47afde295d8b8fedd1
+size 16389

checkpoint-88/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d39c42a0e99b649060daad50babf4f0a789d5aa25709c578baa4c9b3fb6571
+size 16404

checkpoint-88/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:576993ce0cbca547dcc3c3d93624fde489b1dd9d5cd6a7b9ff80f48c676b9492
+size 16404

checkpoint-88/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fb61175b69ddef3dbba3044851653a84498f9702b9f341f0fb23e677428af7
+size 16404

checkpoint-88/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28aadcf527f9aca3ebaaf67d53bb39595758a220ac83128227894564bdd3c1c2
+size 16404

checkpoint-88/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a16b8addd245ff3e664264d67e749d83062d6e188d30b52e503814b4adf1235
+size 16404

checkpoint-88/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b6e967702eced3777973bfee18d0160ebf5ce04fd7b2d58206d3255a70aab7
+size 16404

checkpoint-88/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f556caed1af3ffe6e776d9e46650a640db49fcf4524cf1380a0f2362a9dd7ff
+size 16404

checkpoint-88/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea02ba0176fde363cc125b69b4657e7d63df95630bae08c643f208de8f65f75
+size 16404

checkpoint-88/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13a7bce165b68191a479b7bdea3b84c7d74354340a3d60ea07b6e278a9ddc07
+size 16404

checkpoint-88/rng_state_19.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0de654079193e14bb3c455ef2f8f9e5293bf57f8d411b3c44e7cb3a249e38c
+size 16404

checkpoint-88/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864bf944b7fe59c3d076145cb591c0b4202157a6de0befcb0b5797d05962d20e
+size 16389

checkpoint-88/rng_state_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067f6d8b8579f6425cb6b76596f0886f844506f9186834c5b6e3e989d08df39d
+size 16404

checkpoint-88/rng_state_21.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e131d8cb2422a3bccdb05801b758de2019bf20adf3fe806812fe3da246773c0d
+size 16404

checkpoint-88/rng_state_22.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56232f8010fb324ef8e428a1b59671e3314cf8fa1205604bc9b0d10155f79ba
+size 16404

checkpoint-88/rng_state_23.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1194130652a967ed6e8f01b7f931aab16aaab7854abbe0843fc154d7ef8278d
+size 16404

checkpoint-88/rng_state_24.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596aaddaafbd1422744895e1d31debc933e3476206afb0bd2ede16f38a0a595a
+size 16404

checkpoint-88/rng_state_25.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f842707323aecfd30ff8148cc9bd1d940704a4a573a40f6754079302ee6078
+size 16404

checkpoint-88/rng_state_26.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8808086f3f3e338e55d89e2046a31ca289e2197277c3f34573ef9c47a52fb6ca
+size 16404

checkpoint-88/rng_state_27.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dce8a99e08f9122e6f485ed11452889b063151d8655dad71a38397312df4ec0
+size 16404

checkpoint-88/rng_state_28.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dd7bfb236aade8570d551d55438500104df624a0423ee1587131e3f3dbd6c50
+size 16404

checkpoint-88/rng_state_29.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfb247beaca7fedae2d6d9ce303487f8f50f8020c5dd9f3bd2a19edde072434
+size 16404

checkpoint-88/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d381ca785a7ecce76faa769336d5e9287283042919687663a237440b7f641981
+size 16389

checkpoint-88/rng_state_30.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4cd686b5ced72e3919087efef025a8cc19afd8a1daa780d125f93fc1aca831
+size 16404

checkpoint-88/rng_state_31.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2065bb03ec0cb8c7adfb8e58078f7a2a74088046998c76cbab4d882610f81e0
+size 16404

checkpoint-88/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25b2926e255ab5ac840a9f11eb944262bc85d98693c39982d8dcc3076515a26
+size 16389

checkpoint-88/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1319a784c42a0f542af3dde1ebaf7211e2a2ef58e78f76b15c5559abd34fcd
+size 16389

checkpoint-88/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bb2ebaaa80bc508c22054e7a05130706ae1b7fe42dd5c16e54965b6ce6378b
+size 16389

checkpoint-88/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc096aa1d338785c5fd41f19069a46da703035e2efaf94e33c79fc9d31d068c4
+size 16389

checkpoint-88/rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1758369857e543cf7017900da875d6b45582ed42103ee19b32680d536c7d29
+size 16389

checkpoint-88/rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cfb0453654cdb18b0bd0eebbd8284f35f36cdd03b37e3eda5defe012cbedc1
+size 16389

checkpoint-88/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14d21de0f8a8e8e3bdf3b08844a35b70e11a05a6ed32dd16e673b6b89f5cf61
+size 1465

checkpoint-88/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

checkpoint-88/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}