Upload 11 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: ura-hcmut/GemSUra-7B
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ura-hcmut/GemSUra-7B",
+  "bias": "none",
+  "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": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024d2ab13307a6af41650d5791b60694cd50b85f0c0e275ffc38fd93b3783a72
+size 100059752

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:884546809d67a2f41770ad5398108f88380e73a114e291062b2c739c16c8e4f0
+size 200345450

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905a4ddd7e70ad0205b7e8affc7b73b0a7c2b25c1d62b2b982f3f51ed33a352a
+size 1064

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<eos>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,175 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.930524428507396,
+  "eval_steps": 500,
+  "global_step": 11000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0,
+      "learning_rate": 4.775885253249664e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.0,
+      "learning_rate": 4.551770506499328e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0,
+      "learning_rate": 4.327655759748992e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.0,
+      "learning_rate": 4.1035410129986554e-05,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8794262662483196e-05,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.0,
+      "learning_rate": 3.655311519497983e-05,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.0,
+      "learning_rate": 3.4311967727476465e-05,
+      "loss": 0.0,
+      "step": 3500
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2070820259973107e-05,
+      "loss": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9829672792469748e-05,
+      "loss": 0.0,
+      "step": 4500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7588525324966386e-05,
+      "loss": 0.0,
+      "step": 5000
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5347377857463024e-05,
+      "loss": 0.0,
+      "step": 5500
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.0,
+      "learning_rate": 2.310623038995966e-05,
+      "loss": 0.0,
+      "step": 6000
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.0,
+      "learning_rate": 2.08650829224563e-05,
+      "loss": 0.0,
+      "step": 6500
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8623935454952938e-05,
+      "loss": 0.0,
+      "step": 7000
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.0,
+      "learning_rate": 1.6382787987449573e-05,
+      "loss": 0.0,
+      "step": 7500
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4141640519946214e-05,
+      "loss": 0.0,
+      "step": 8000
+    },
+    {
+      "epoch": 3.81,
+      "grad_norm": 0.0,
+      "learning_rate": 1.1900493052442852e-05,
+      "loss": 0.0,
+      "step": 8500
+    },
+    {
+      "epoch": 4.03,
+      "grad_norm": 0.0,
+      "learning_rate": 9.65934558493949e-06,
+      "loss": 0.0,
+      "step": 9000
+    },
+    {
+      "epoch": 4.26,
+      "grad_norm": 0.0,
+      "learning_rate": 7.418198117436127e-06,
+      "loss": 0.0,
+      "step": 9500
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.0,
+      "learning_rate": 5.177050649932766e-06,
+      "loss": 0.0,
+      "step": 10000
+    },
+    {
+      "epoch": 4.71,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9359031824294042e-06,
+      "loss": 0.0,
+      "step": 10500
+    },
+    {
+      "epoch": 4.93,
+      "grad_norm": 0.0,
+      "learning_rate": 6.947557149260422e-07,
+      "loss": 0.0,
+      "step": 11000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11155,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.781601348825047e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ae37695931553a8e96ea08277799c55708a47e5f44c927b6a877200585769e
+size 4856