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": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_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 sha256:8b169a1e1e4be8272649f1f3f736310ec9fac63a91867eca4ee74558c715968e
+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": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "down_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 sha256:8b169a1e1e4be8272649f1f3f736310ec9fac63a91867eca4ee74558c715968e
+size 78480072

checkpoint-396/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a4917c50959d9ebdb4fe5f89e0ecca27cec734375fd0a68e10b0c9698b4fbb
+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:d88d86fc4fb9e3ce481e45c3ba39b4c3c3510eb8f7006191533eafa8f076ea64
+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": 0.0009370408370159566,
+      "learning_rate": 1.95e-05,
+      "logits/chosen": -22.68578338623047,
+      "logits/rejected": -22.825130462646484,
+      "logps/chosen": -78.43010711669922,
+      "logps/rejected": -102.63253784179688,
+      "loss": 0.1807,
+      "rewards/accuracies": 0.9230769276618958,
+      "rewards/chosen": 2.8142247200012207,
+      "rewards/margins": 4.811609268188477,
+      "rewards/rejected": -1.997384786605835,
+      "step": 26
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.192274041590281e-05,
+      "learning_rate": 2.8988764044943823e-05,
+      "logits/chosen": -23.15672492980957,
+      "logits/rejected": -23.271657943725586,
+      "logps/chosen": -43.96305465698242,
+      "logps/rejected": -155.8493194580078,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.304109573364258,
+      "rewards/margins": 13.57724380493164,
+      "rewards/rejected": -7.273132801055908,
+      "step": 52
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.914922904688865e-05,
+      "learning_rate": 2.6797752808988762e-05,
+      "logits/chosen": -23.230398178100586,
+      "logits/rejected": -23.34272575378418,
+      "logps/chosen": -42.47319030761719,
+      "logps/rejected": -166.07025146484375,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.426936149597168,
+      "rewards/margins": 14.743646621704102,
+      "rewards/rejected": -8.316710472106934,
+      "step": 78
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.923706804518588e-05,
+      "learning_rate": 2.4606741573033708e-05,
+      "logits/chosen": -23.297359466552734,
+      "logits/rejected": -23.406126022338867,
+      "logps/chosen": -42.298927307128906,
+      "logps/rejected": -167.82479858398438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4410505294799805,
+      "rewards/margins": 14.930893898010254,
+      "rewards/rejected": -8.48984432220459,
+      "step": 104
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.00013795163249596953,
+      "learning_rate": 2.2415730337078654e-05,
+      "logits/chosen": -23.36400032043457,
+      "logits/rejected": -23.47435760498047,
+      "logps/chosen": -42.36582565307617,
+      "logps/rejected": -167.81008911132812,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.42643404006958,
+      "rewards/margins": 14.924281120300293,
+      "rewards/rejected": -8.497847557067871,
+      "step": 130
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.9170562154613435e-05,
+      "learning_rate": 2.0224719101123596e-05,
+      "logits/chosen": -23.275028228759766,
+      "logits/rejected": -23.385255813598633,
+      "logps/chosen": -42.21509552001953,
+      "logps/rejected": -167.64584350585938,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.436044692993164,
+      "rewards/margins": 14.92562198638916,
+      "rewards/rejected": -8.48957633972168,
+      "step": 156
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.7988468243856914e-05,
+      "learning_rate": 1.803370786516854e-05,
+      "logits/chosen": -23.300710678100586,
+      "logits/rejected": -23.410503387451172,
+      "logps/chosen": -42.11836624145508,
+      "logps/rejected": -169.15122985839844,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.481032371520996,
+      "rewards/margins": 15.097738265991211,
+      "rewards/rejected": -8.616707801818848,
+      "step": 182
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 2.1618798200506717e-05,
+      "learning_rate": 1.5842696629213484e-05,
+      "logits/chosen": -23.332603454589844,
+      "logits/rejected": -23.443927764892578,
+      "logps/chosen": -42.54871368408203,
+      "logps/rejected": -167.39431762695312,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.385127067565918,
+      "rewards/margins": 14.849527359008789,
+      "rewards/rejected": -8.464401245117188,
+      "step": 208
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.6424854038632475e-05,
+      "learning_rate": 1.3651685393258428e-05,
+      "logits/chosen": -23.301807403564453,
+      "logits/rejected": -23.41258430480957,
+      "logps/chosen": -42.13775634765625,
+      "logps/rejected": -168.62362670898438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.500583171844482,
+      "rewards/margins": 15.051546096801758,
+      "rewards/rejected": -8.550962448120117,
+      "step": 234
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 1.6196921933442354e-05,
+      "learning_rate": 1.146067415730337e-05,
+      "logits/chosen": -23.335044860839844,
+      "logits/rejected": -23.44767951965332,
+      "logps/chosen": -42.26608657836914,
+      "logps/rejected": -167.9331817626953,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.42073917388916,
+      "rewards/margins": 14.927839279174805,
+      "rewards/rejected": -8.507099151611328,
+      "step": 260
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 1.7393831512890756e-05,
+      "learning_rate": 9.269662921348314e-06,
+      "logits/chosen": -23.317138671875,
+      "logits/rejected": -23.424781799316406,
+      "logps/chosen": -41.94506072998047,
+      "logps/rejected": -168.30055236816406,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.4749298095703125,
+      "rewards/margins": 15.034900665283203,
+      "rewards/rejected": -8.55997085571289,
+      "step": 286
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 1.7613503587199375e-05,
+      "learning_rate": 7.078651685393258e-06,
+      "logits/chosen": -23.292570114135742,
+      "logits/rejected": -23.40188217163086,
+      "logps/chosen": -42.209102630615234,
+      "logps/rejected": -169.81747436523438,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.467267990112305,
+      "rewards/margins": 15.145313262939453,
+      "rewards/rejected": -8.678045272827148,
+      "step": 312
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.0001227569446200505,
+      "learning_rate": 4.8876404494382024e-06,
+      "logits/chosen": -23.324228286743164,
+      "logits/rejected": -23.43165397644043,
+      "logps/chosen": -41.959617614746094,
+      "logps/rejected": -169.5789337158203,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.512591361999512,
+      "rewards/margins": 15.166027069091797,
+      "rewards/rejected": -8.653436660766602,
+      "step": 338
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 1.6931946447584778e-05,
+      "learning_rate": 2.696629213483146e-06,
+      "logits/chosen": -23.30262565612793,
+      "logits/rejected": -23.414592742919922,
+      "logps/chosen": -42.351627349853516,
+      "logps/rejected": -168.41354370117188,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.420273780822754,
+      "rewards/margins": 14.962029457092285,
+      "rewards/rejected": -8.541756629943848,
+      "step": 364
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 1.576123213453684e-05,
+      "learning_rate": 5.056179775280899e-07,
+      "logits/chosen": -23.35226058959961,
+      "logits/rejected": -23.466854095458984,
+      "logps/chosen": -42.21808624267578,
+      "logps/rejected": -168.39918518066406,
+      "loss": 0.0,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 6.449341297149658,
+      "rewards/margins": 15.006133079528809,
+      "rewards/rejected": -8.556791305541992,
+      "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:cb860eaf85aafc1d3412d367086a23dd15fa1fb7758535b990646abd0a91e3ec
+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_15-42-24_r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub/events.out.tfevents.1710603751.r-mjmanashti-fine-tuning-vw6mcjeh-b4da6-f8cub.55.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901ccfd6cbeaee38eddad2e91629d6b4229224a3b665053f3474fe9c4613861e
-size 14631
+oid sha256:3414fcd2baf9e09cfa899d3f19599fccb0418ffd79e19709f875fcd1c340bb4d
+size 15673

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:cb860eaf85aafc1d3412d367086a23dd15fa1fb7758535b990646abd0a91e3ec
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "google/gemma-2b-it",
+    "project_name": "autotrain-gemma",
+    "data_path": "autotrain-gemma/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-gemma",
+    "username": "mjmanashti"
+}