Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: models/tofu_ft_llama2-7b
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+    "alpha_pattern": {},
+    "auto_mapping": null,
+    "base_model_name_or_path": "locuslab/tofu_ft_llama2-7b",
+    "bias": "none",
+    "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,
+    "megatron_config": null,
+    "megatron_core": "megatron.core",
+    "modules_to_save": null,
+    "peft_type": "LORA",
+    "r": 8,
+    "rank_pattern": {},
+    "revision": null,
+    "target_modules": [
+        "q_proj",
+        "k_proj",
+        "o_proj",
+        "gate_proj",
+        "up_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:cb43d69ee792ac3993d657761a86a359eec7a4aad3a8f2a4eb4a4ac76510d1cc
+size 40036488

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,180 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 150.0,
+  "eval_steps": 0,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.0,
+      "grad_norm": 48.4139042121476,
+      "learning_rate": 9.59731543624161e-06,
+      "loss": -1.7565,
+      "step": 7
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 52.59146449904736,
+      "learning_rate": 9.12751677852349e-06,
+      "loss": -1.7613,
+      "step": 14
+    },
+    {
+      "epoch": 21.0,
+      "grad_norm": 47.26514678968975,
+      "learning_rate": 8.65771812080537e-06,
+      "loss": -3.3713,
+      "step": 21
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 46.58180426373221,
+      "learning_rate": 8.18791946308725e-06,
+      "loss": -3.2182,
+      "step": 28
+    },
+    {
+      "epoch": 35.0,
+      "grad_norm": 49.96836818031308,
+      "learning_rate": 7.718120805369127e-06,
+      "loss": -4.3871,
+      "step": 35
+    },
+    {
+      "epoch": 42.0,
+      "grad_norm": 51.36942343142531,
+      "learning_rate": 7.248322147651007e-06,
+      "loss": -6.0204,
+      "step": 42
+    },
+    {
+      "epoch": 49.0,
+      "grad_norm": 57.98074681502372,
+      "learning_rate": 6.778523489932887e-06,
+      "loss": -7.6868,
+      "step": 49
+    },
+    {
+      "epoch": 56.0,
+      "grad_norm": 63.94053871326419,
+      "learning_rate": 6.308724832214766e-06,
+      "loss": -8.3268,
+      "step": 56
+    },
+    {
+      "epoch": 63.0,
+      "grad_norm": 69.6805815155802,
+      "learning_rate": 5.8389261744966455e-06,
+      "loss": -10.5719,
+      "step": 63
+    },
+    {
+      "epoch": 70.0,
+      "grad_norm": 67.34407931241151,
+      "learning_rate": 5.369127516778524e-06,
+      "loss": -11.0897,
+      "step": 70
+    },
+    {
+      "epoch": 77.0,
+      "grad_norm": 67.18560177039734,
+      "learning_rate": 4.899328859060403e-06,
+      "loss": -12.9657,
+      "step": 77
+    },
+    {
+      "epoch": 84.0,
+      "grad_norm": 65.05528975579614,
+      "learning_rate": 4.429530201342283e-06,
+      "loss": -13.5019,
+      "step": 84
+    },
+    {
+      "epoch": 91.0,
+      "grad_norm": 68.36811466181042,
+      "learning_rate": 3.959731543624161e-06,
+      "loss": -14.4435,
+      "step": 91
+    },
+    {
+      "epoch": 98.0,
+      "grad_norm": 61.60167621847075,
+      "learning_rate": 3.4899328859060407e-06,
+      "loss": -15.6623,
+      "step": 98
+    },
+    {
+      "epoch": 105.0,
+      "grad_norm": 64.00094153911085,
+      "learning_rate": 3.02013422818792e-06,
+      "loss": -17.1393,
+      "step": 105
+    },
+    {
+      "epoch": 112.0,
+      "grad_norm": 63.87128213160341,
+      "learning_rate": 2.5503355704697992e-06,
+      "loss": -17.6534,
+      "step": 112
+    },
+    {
+      "epoch": 119.0,
+      "grad_norm": 64.38897540669797,
+      "learning_rate": 2.080536912751678e-06,
+      "loss": -18.0848,
+      "step": 119
+    },
+    {
+      "epoch": 126.0,
+      "grad_norm": 69.13070299837193,
+      "learning_rate": 1.6107382550335572e-06,
+      "loss": -18.2882,
+      "step": 126
+    },
+    {
+      "epoch": 133.0,
+      "grad_norm": 77.86614653780259,
+      "learning_rate": 1.1409395973154363e-06,
+      "loss": -18.8161,
+      "step": 133
+    },
+    {
+      "epoch": 140.0,
+      "grad_norm": 71.46054590772218,
+      "learning_rate": 6.711409395973155e-07,
+      "loss": -19.1841,
+      "step": 140
+    },
+    {
+      "epoch": 147.0,
+      "grad_norm": 69.2287092573417,
+      "learning_rate": 2.0134228187919465e-07,
+      "loss": -19.8017,
+      "step": 147
+    }
+  ],
+  "logging_steps": 7,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 150,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02204590ca6ee875398ab9459b0575cf74f97269f69c2d3dfb7a068093bd7fc4
+size 6968