Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-396/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_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 sha256:90781f69a5e28914611ac71b91cb8266be2fa682ac481e8ad9132efa42d6baf4
+size 78480072

checkpoint-396/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b-it
+---
+
+# 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 0.9.0

checkpoint-396/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-396/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90781f69a5e28914611ac71b91cb8266be2fa682ac481e8ad9132efa42d6baf4
+size 78480072

checkpoint-396/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa9eaaed96de9f8e703b99aeb818b5148ab85605f3bd37e458006d05d09a809
+size 157104826

checkpoint-396/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
+size 888

checkpoint-396/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-396/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57964bbfefdaa0007fbf6bb66063ef0bade3a8e436f7cbda4cf2b9d2d025c03b
+size 1064

checkpoint-396/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-396/tokenizer.json

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

checkpoint-396/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

checkpoint-396/tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-396/trainer_state.json

@@ -0,0 +1,246 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 396,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0012223966186866164,
+      "learning_rate": 1.8750000000000002e-05,
+      "logits/chosen": -22.664844512939453,
+      "logits/rejected": -22.80691909790039,
+      "logps/chosen": -81.01699829101562,
+      "logps/rejected": -101.25294494628906,
+      "loss": 0.2072,
+      "rewards/accuracies": 0.8846153616905212,
+      "rewards/chosen": 2.5555355548858643,
+      "rewards/margins": 4.414959907531738,
+      "rewards/rejected": -1.859424352645874,
+      "step": 26
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.8405307855573483e-05,
+      "learning_rate": 2.9073033707865168e-05,
+      "logits/chosen": -23.12621307373047,
+      "logits/rejected": -23.24854278564453,
+      "logps/chosen": -43.78964614868164,
+      "logps/rejected": -156.3304901123047,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.3214497566223145,
+      "rewards/margins": 13.642704010009766,
+      "rewards/rejected": -7.321253776550293,
+      "step": 52
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.5625999367330223e-05,
+      "learning_rate": 2.6882022471910113e-05,
+      "logits/chosen": -23.210811614990234,
+      "logits/rejected": -23.32987403869629,
+      "logps/chosen": -41.96815490722656,
+      "logps/rejected": -167.406982421875,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.477440357208252,
+      "rewards/margins": 14.927824020385742,
+      "rewards/rejected": -8.450382232666016,
+      "step": 78
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.5885076209087856e-05,
+      "learning_rate": 2.4691011235955056e-05,
+      "logits/chosen": -23.275333404541016,
+      "logits/rejected": -23.39052391052246,
+      "logps/chosen": -41.763607025146484,
+      "logps/rejected": -169.25025939941406,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4945831298828125,
+      "rewards/margins": 15.126973152160645,
+      "rewards/rejected": -8.632390975952148,
+      "step": 104
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.00013870897237211466,
+      "learning_rate": 2.25e-05,
+      "logits/chosen": -23.342487335205078,
+      "logits/rejected": -23.45945167541504,
+      "logps/chosen": -41.83483123779297,
+      "logps/rejected": -169.22845458984375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.479532718658447,
+      "rewards/margins": 15.119216918945312,
+      "rewards/rejected": -8.63968276977539,
+      "step": 130
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.5738529327791184e-05,
+      "learning_rate": 2.0308988764044947e-05,
+      "logits/chosen": -23.253267288208008,
+      "logits/rejected": -23.370222091674805,
+      "logps/chosen": -41.68398666381836,
+      "logps/rejected": -169.04989624023438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4891557693481445,
+      "rewards/margins": 15.119135856628418,
+      "rewards/rejected": -8.629980087280273,
+      "step": 156
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.4681028005725238e-05,
+      "learning_rate": 1.8117977528089886e-05,
+      "logits/chosen": -23.281639099121094,
+      "logits/rejected": -23.397907257080078,
+      "logps/chosen": -41.55263137817383,
+      "logps/rejected": -170.5806427001953,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.5376057624816895,
+      "rewards/margins": 15.297250747680664,
+      "rewards/rejected": -8.759647369384766,
+      "step": 182
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.823231104935985e-05,
+      "learning_rate": 1.5926966292134832e-05,
+      "logits/chosen": -23.312273025512695,
+      "logits/rejected": -23.43006706237793,
+      "logps/chosen": -42.09364318847656,
+      "logps/rejected": -168.72459411621094,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.430633544921875,
+      "rewards/margins": 15.028059959411621,
+      "rewards/rejected": -8.597426414489746,
+      "step": 208
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.3677333299710881e-05,
+      "learning_rate": 1.3735955056179776e-05,
+      "logits/chosen": -23.281251907348633,
+      "logits/rejected": -23.39859390258789,
+      "logps/chosen": -41.60188293457031,
+      "logps/rejected": -169.98341369628906,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.554170608520508,
+      "rewards/margins": 15.241110801696777,
+      "rewards/rejected": -8.686941146850586,
+      "step": 234
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.329195401922334e-05,
+      "learning_rate": 1.154494382022472e-05,
+      "logits/chosen": -23.316593170166016,
+      "logits/rejected": -23.435791015625,
+      "logps/chosen": -41.78284454345703,
+      "logps/rejected": -169.241943359375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4690632820129395,
+      "rewards/margins": 15.107036590576172,
+      "rewards/rejected": -8.63797378540039,
+      "step": 260
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 1.4401819498743862e-05,
+      "learning_rate": 9.353932584269662e-06,
+      "logits/chosen": -23.297456741333008,
+      "logits/rejected": -23.411481857299805,
+      "logps/chosen": -41.401039123535156,
+      "logps/rejected": -169.64952087402344,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.529332160949707,
+      "rewards/margins": 15.224197387695312,
+      "rewards/rejected": -8.694866180419922,
+      "step": 286
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.4643008398707025e-05,
+      "learning_rate": 7.162921348314607e-06,
+      "logits/chosen": -23.277320861816406,
+      "logits/rejected": -23.393136978149414,
+      "logps/chosen": -41.65689468383789,
+      "logps/rejected": -171.18663024902344,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.522489070892334,
+      "rewards/margins": 15.33745002746582,
+      "rewards/rejected": -8.814961433410645,
+      "step": 312
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.00012409774353727698,
+      "learning_rate": 4.97191011235955e-06,
+      "logits/chosen": -23.303037643432617,
+      "logits/rejected": -23.417268753051758,
+      "logps/chosen": -41.39340591430664,
+      "logps/rejected": -170.94407653808594,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.569211483001709,
+      "rewards/margins": 15.359162330627441,
+      "rewards/rejected": -8.789949417114258,
+      "step": 338
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.4201951671566349e-05,
+      "learning_rate": 2.7808988764044947e-06,
+      "logits/chosen": -23.281291961669922,
+      "logits/rejected": -23.399757385253906,
+      "logps/chosen": -41.88224792480469,
+      "logps/rejected": -169.70294189453125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4672112464904785,
+      "rewards/margins": 15.137907028198242,
+      "rewards/rejected": -8.670695304870605,
+      "step": 364
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.3474539628077764e-05,
+      "learning_rate": 5.898876404494382e-07,
+      "logits/chosen": -23.33159065246582,
+      "logits/rejected": -23.45261573791504,
+      "logps/chosen": -41.745670318603516,
+      "logps/rejected": -169.70147705078125,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.496582984924316,
+      "rewards/margins": 15.183600425720215,
+      "rewards/rejected": -8.687018394470215,
+      "step": 390
+    }
+  ],
+  "logging_steps": 26,
+  "max_steps": 396,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-396/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b66944c6ba8ce2a8b2c27e6bbc7c9fabf4c22d6751a552189abe34c9340639
+size 4920

handler.py

@@ -0,0 +1,32 @@
+from typing import  Dict, List, Any
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+import torch
+from peft import PeftModel
+import json
+import os
+
+
+class EndpointHandler():
+    def __init__(self, path=""):
+        base_model_path = json.load(open(os.path.join(path, "training_params.json")))["model"]
+        model = AutoModelForCausalLM.from_pretrained(
+            base_model_path,
+            torch_dtype=torch.float16,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            device_map="auto",
+        )
+        tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)
+        model.resize_token_embeddings(len(tokenizer))
+        model = PeftModel.from_pretrained(model, path)
+        model = model.merge_and_unload()
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+        if parameters is not None:
+            prediction = self.pipeline(inputs, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        return prediction

requirements.txt

@@ -0,0 +1,2 @@
+peft==0.9.0
+transformers==4.38.2

runs/Mar16_16-26-20_r-mjmanashti-fine-tuning-3acqz3c0-e32eb-8nbhd/events.out.tfevents.1710606388.r-mjmanashti-fine-tuning-3acqz3c0-e32eb-8nbhd.54.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0ae891666127019fb4a674ba0911b276e84cbc441979c99938cd531566b20f
-size 14649
+oid sha256:d5deaabcc34586e8ca125f174a895225344475787a57ce3083af954f801fbb15
+size 15691

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b66944c6ba8ce2a8b2c27e6bbc7c9fabf4c22d6751a552189abe34c9340639
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "google/gemma-2b-it",
+    "project_name": "autotrain-cff1t-gk81o",
+    "data_path": "autotrain-cff1t-gk81o/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "dpo",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 1,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "autotrain_prompt",
+    "text_column": "autotrain_text",
+    "rejected_text_column": "autotrain_rejected_text",
+    "push_to_hub": true,
+    "repo_id": "mjmanashti/autotrain-cff1t-gk81o",
+    "username": "mjmanashti"
+}