Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/codellama-7b-bnb-4bit
+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": "unsloth/codellama-7b-bnb-4bit",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_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:f5345fb4aa46e4c4203413c74bb301263c96159ff3bd764c73af6c10710ce232
+size 159967880

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,89 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,383 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.571428571428571,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.11384429782629013,
+      "learning_rate": 9.940119760479042e-05,
+      "loss": 1.1555,
+      "step": 10
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.18670473992824554,
+      "learning_rate": 9.820359281437126e-05,
+      "loss": 0.986,
+      "step": 20
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.1131674274802208,
+      "learning_rate": 9.700598802395209e-05,
+      "loss": 0.6862,
+      "step": 30
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.09851589798927307,
+      "learning_rate": 9.580838323353294e-05,
+      "loss": 0.6073,
+      "step": 40
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.07161638140678406,
+      "learning_rate": 9.461077844311378e-05,
+      "loss": 0.5746,
+      "step": 50
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.060462553054094315,
+      "learning_rate": 9.341317365269462e-05,
+      "loss": 0.568,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.06703554838895798,
+      "learning_rate": 9.221556886227547e-05,
+      "loss": 0.571,
+      "step": 70
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.06138037517666817,
+      "learning_rate": 9.101796407185628e-05,
+      "loss": 0.5884,
+      "step": 80
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.06791023164987564,
+      "learning_rate": 8.982035928143712e-05,
+      "loss": 0.5681,
+      "step": 90
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.06872102618217468,
+      "learning_rate": 8.862275449101797e-05,
+      "loss": 0.5602,
+      "step": 100
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.07038596272468567,
+      "learning_rate": 8.742514970059881e-05,
+      "loss": 0.5587,
+      "step": 110
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.07541386038064957,
+      "learning_rate": 8.622754491017964e-05,
+      "loss": 0.5442,
+      "step": 120
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.09144806116819382,
+      "learning_rate": 8.502994011976048e-05,
+      "loss": 0.5272,
+      "step": 130
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.10239645093679428,
+      "learning_rate": 8.383233532934131e-05,
+      "loss": 0.5709,
+      "step": 140
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.0748690515756607,
+      "learning_rate": 8.263473053892216e-05,
+      "loss": 0.5114,
+      "step": 150
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.08167172223329544,
+      "learning_rate": 8.1437125748503e-05,
+      "loss": 0.5227,
+      "step": 160
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.1070200651884079,
+      "learning_rate": 8.023952095808383e-05,
+      "loss": 0.5444,
+      "step": 170
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.09023091942071915,
+      "learning_rate": 7.904191616766467e-05,
+      "loss": 0.5313,
+      "step": 180
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.11614037305116653,
+      "learning_rate": 7.784431137724552e-05,
+      "loss": 0.5109,
+      "step": 190
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.09616102278232574,
+      "learning_rate": 7.664670658682636e-05,
+      "loss": 0.5205,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.1161426305770874,
+      "learning_rate": 7.544910179640719e-05,
+      "loss": 0.4951,
+      "step": 210
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.11568252742290497,
+      "learning_rate": 7.425149700598802e-05,
+      "loss": 0.5076,
+      "step": 220
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.09209095686674118,
+      "learning_rate": 7.305389221556886e-05,
+      "loss": 0.4703,
+      "step": 230
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.11663572490215302,
+      "learning_rate": 7.18562874251497e-05,
+      "loss": 0.5073,
+      "step": 240
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.11245130747556686,
+      "learning_rate": 7.065868263473055e-05,
+      "loss": 0.4897,
+      "step": 250
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.12360594421625137,
+      "learning_rate": 6.946107784431138e-05,
+      "loss": 0.5232,
+      "step": 260
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.11183296144008636,
+      "learning_rate": 6.826347305389222e-05,
+      "loss": 0.5185,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13983388245105743,
+      "learning_rate": 6.706586826347305e-05,
+      "loss": 0.4794,
+      "step": 280
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": 0.11507315188646317,
+      "learning_rate": 6.58682634730539e-05,
+      "loss": 0.4637,
+      "step": 290
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.13093125820159912,
+      "learning_rate": 6.467065868263474e-05,
+      "loss": 0.4681,
+      "step": 300
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": 0.13779377937316895,
+      "learning_rate": 6.347305389221557e-05,
+      "loss": 0.4643,
+      "step": 310
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.14057691395282745,
+      "learning_rate": 6.227544910179641e-05,
+      "loss": 0.5048,
+      "step": 320
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": 0.12082990258932114,
+      "learning_rate": 6.107784431137725e-05,
+      "loss": 0.4655,
+      "step": 330
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.16593365371227264,
+      "learning_rate": 5.988023952095808e-05,
+      "loss": 0.4419,
+      "step": 340
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.13827389478683472,
+      "learning_rate": 5.868263473053892e-05,
+      "loss": 0.4505,
+      "step": 350
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.13826914131641388,
+      "learning_rate": 5.748502994011976e-05,
+      "loss": 0.4786,
+      "step": 360
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": 0.13597093522548676,
+      "learning_rate": 5.62874251497006e-05,
+      "loss": 0.4541,
+      "step": 370
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.16901850700378418,
+      "learning_rate": 5.508982035928144e-05,
+      "loss": 0.4613,
+      "step": 380
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": 0.15610496699810028,
+      "learning_rate": 5.389221556886228e-05,
+      "loss": 0.4725,
+      "step": 390
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.14943359792232513,
+      "learning_rate": 5.269461077844312e-05,
+      "loss": 0.4736,
+      "step": 400
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": 0.15164442360401154,
+      "learning_rate": 5.149700598802395e-05,
+      "loss": 0.4526,
+      "step": 410
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.19106097519397736,
+      "learning_rate": 5.029940119760479e-05,
+      "loss": 0.5182,
+      "step": 420
+    },
+    {
+      "epoch": 3.0714285714285716,
+      "grad_norm": 0.1616070717573166,
+      "learning_rate": 4.910179640718563e-05,
+      "loss": 0.4176,
+      "step": 430
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.1612323522567749,
+      "learning_rate": 4.790419161676647e-05,
+      "loss": 0.4299,
+      "step": 440
+    },
+    {
+      "epoch": 3.2142857142857144,
+      "grad_norm": 0.16307303309440613,
+      "learning_rate": 4.670658682634731e-05,
+      "loss": 0.4555,
+      "step": 450
+    },
+    {
+      "epoch": 3.2857142857142856,
+      "grad_norm": 0.18952146172523499,
+      "learning_rate": 4.550898203592814e-05,
+      "loss": 0.4005,
+      "step": 460
+    },
+    {
+      "epoch": 3.357142857142857,
+      "grad_norm": 0.1773829460144043,
+      "learning_rate": 4.4311377245508984e-05,
+      "loss": 0.4258,
+      "step": 470
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 0.1871429979801178,
+      "learning_rate": 4.311377245508982e-05,
+      "loss": 0.4363,
+      "step": 480
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.19548629224300385,
+      "learning_rate": 4.191616766467066e-05,
+      "loss": 0.4218,
+      "step": 490
+    },
+    {
+      "epoch": 3.571428571428571,
+      "grad_norm": 0.17752481997013092,
+      "learning_rate": 4.07185628742515e-05,
+      "loss": 0.4383,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 4.06922293442347e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}