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-4040/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",
+  "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": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "q_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 sha256:4ca547a361a90013863d28dfaa5885873fe7adcad4a3e01d801eb60a3de92fcd
+size 78480072

checkpoint-4040/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: google/gemma-2b
+---
+
+# 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-4040/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "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": [
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-4040/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca547a361a90013863d28dfaa5885873fe7adcad4a3e01d801eb60a3de92fcd
+size 78480072

checkpoint-4040/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4b2836ed2b16fb09b5d8e1a1e327403e334dc27880767e249ba647e409e1c7
+size 157104826

checkpoint-4040/pytorch_model.bin

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

checkpoint-4040/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558827980d72547dab3996c8477bd8ca92d3995995bca613a1fb28c743f1d820
+size 14244

checkpoint-4040/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c228739c5078729a78b85e506a3169a7a4556d92c9abdc788dd4bb10220d27db
+size 1064

checkpoint-4040/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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-4040/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

checkpoint-4040/tokenizer.model

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

checkpoint-4040/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\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-4040/trainer_state.json

@@ -0,0 +1,371 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 13.334685325622559,
+      "learning_rate": 5.7178217821782184e-06,
+      "loss": 2.6835,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.5441126823425293,
+      "learning_rate": 1.1584158415841584e-05,
+      "loss": 2.3047,
+      "step": 160
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.4855196475982666,
+      "learning_rate": 1.7524752475247524e-05,
+      "loss": 2.0103,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.429617166519165,
+      "learning_rate": 2.3465346534653467e-05,
+      "loss": 1.7695,
+      "step": 320
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.6394236087799072,
+      "learning_rate": 2.9405940594059407e-05,
+      "loss": 1.7141,
+      "step": 400
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 4.821674823760986,
+      "learning_rate": 2.9405940594059407e-05,
+      "loss": 1.6202,
+      "step": 480
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.7676095962524414,
+      "learning_rate": 2.8745874587458746e-05,
+      "loss": 1.5316,
+      "step": 560
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 1.9537432193756104,
+      "learning_rate": 2.8085808580858088e-05,
+      "loss": 1.5497,
+      "step": 640
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 1.6451698541641235,
+      "learning_rate": 2.7425742574257424e-05,
+      "loss": 1.5092,
+      "step": 720
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.8162490129470825,
+      "learning_rate": 2.6765676567656766e-05,
+      "loss": 1.4958,
+      "step": 800
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.7349311113357544,
+      "learning_rate": 2.610561056105611e-05,
+      "loss": 1.4255,
+      "step": 880
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.0465753078460693,
+      "learning_rate": 2.5445544554455447e-05,
+      "loss": 1.4322,
+      "step": 960
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 2.079873561859131,
+      "learning_rate": 2.4785478547854786e-05,
+      "loss": 1.391,
+      "step": 1040
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 1.8764556646347046,
+      "learning_rate": 2.4125412541254125e-05,
+      "loss": 1.4254,
+      "step": 1120
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 2.345323324203491,
+      "learning_rate": 2.3465346534653467e-05,
+      "loss": 1.4177,
+      "step": 1200
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 2.4153122901916504,
+      "learning_rate": 2.2805280528052803e-05,
+      "loss": 1.31,
+      "step": 1280
+    },
+    {
+      "epoch": 3.37,
+      "grad_norm": 2.362084150314331,
+      "learning_rate": 2.2145214521452145e-05,
+      "loss": 1.2966,
+      "step": 1360
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 2.2319586277008057,
+      "learning_rate": 2.1485148514851487e-05,
+      "loss": 1.3684,
+      "step": 1440
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 2.043566942214966,
+      "learning_rate": 2.0825082508250826e-05,
+      "loss": 1.392,
+      "step": 1520
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.2719879150390625,
+      "learning_rate": 2.0165016501650165e-05,
+      "loss": 1.3083,
+      "step": 1600
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 2.6207830905914307,
+      "learning_rate": 1.9504950495049504e-05,
+      "loss": 1.252,
+      "step": 1680
+    },
+    {
+      "epoch": 4.36,
+      "grad_norm": 2.797555446624756,
+      "learning_rate": 1.8844884488448846e-05,
+      "loss": 1.2673,
+      "step": 1760
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 2.4675941467285156,
+      "learning_rate": 1.8184818481848185e-05,
+      "loss": 1.2311,
+      "step": 1840
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 2.450917959213257,
+      "learning_rate": 1.7524752475247524e-05,
+      "loss": 1.2466,
+      "step": 1920
+    },
+    {
+      "epoch": 4.95,
+      "grad_norm": 2.9076478481292725,
+      "learning_rate": 1.6864686468646866e-05,
+      "loss": 1.3578,
+      "step": 2000
+    },
+    {
+      "epoch": 5.15,
+      "grad_norm": 2.909982681274414,
+      "learning_rate": 1.6204620462046205e-05,
+      "loss": 1.2384,
+      "step": 2080
+    },
+    {
+      "epoch": 5.35,
+      "grad_norm": 2.7267675399780273,
+      "learning_rate": 1.5544554455445548e-05,
+      "loss": 1.1951,
+      "step": 2160
+    },
+    {
+      "epoch": 5.54,
+      "grad_norm": 3.54055118560791,
+      "learning_rate": 1.4884488448844885e-05,
+      "loss": 1.2141,
+      "step": 2240
+    },
+    {
+      "epoch": 5.74,
+      "grad_norm": 2.72868275642395,
+      "learning_rate": 1.4224422442244225e-05,
+      "loss": 1.2374,
+      "step": 2320
+    },
+    {
+      "epoch": 5.94,
+      "grad_norm": 2.7000038623809814,
+      "learning_rate": 1.3564356435643564e-05,
+      "loss": 1.2645,
+      "step": 2400
+    },
+    {
+      "epoch": 6.14,
+      "grad_norm": 3.291171073913574,
+      "learning_rate": 1.2904290429042905e-05,
+      "loss": 1.1701,
+      "step": 2480
+    },
+    {
+      "epoch": 6.34,
+      "grad_norm": 2.9283392429351807,
+      "learning_rate": 1.2244224422442244e-05,
+      "loss": 1.1559,
+      "step": 2560
+    },
+    {
+      "epoch": 6.53,
+      "grad_norm": 3.4444239139556885,
+      "learning_rate": 1.1584158415841584e-05,
+      "loss": 1.1984,
+      "step": 2640
+    },
+    {
+      "epoch": 6.73,
+      "grad_norm": 3.4505791664123535,
+      "learning_rate": 1.0924092409240923e-05,
+      "loss": 1.1956,
+      "step": 2720
+    },
+    {
+      "epoch": 6.93,
+      "grad_norm": 3.7554521560668945,
+      "learning_rate": 1.0264026402640264e-05,
+      "loss": 1.1743,
+      "step": 2800
+    },
+    {
+      "epoch": 7.13,
+      "grad_norm": 3.4612154960632324,
+      "learning_rate": 9.603960396039604e-06,
+      "loss": 1.1505,
+      "step": 2880
+    },
+    {
+      "epoch": 7.33,
+      "grad_norm": 3.5600943565368652,
+      "learning_rate": 8.943894389438945e-06,
+      "loss": 1.1334,
+      "step": 2960
+    },
+    {
+      "epoch": 7.52,
+      "grad_norm": 3.4435224533081055,
+      "learning_rate": 8.283828382838284e-06,
+      "loss": 1.1477,
+      "step": 3040
+    },
+    {
+      "epoch": 7.72,
+      "grad_norm": 3.559251546859741,
+      "learning_rate": 7.6237623762376246e-06,
+      "loss": 1.1525,
+      "step": 3120
+    },
+    {
+      "epoch": 7.92,
+      "grad_norm": 4.093379497528076,
+      "learning_rate": 6.9636963696369635e-06,
+      "loss": 1.1258,
+      "step": 3200
+    },
+    {
+      "epoch": 8.12,
+      "grad_norm": 3.836825370788574,
+      "learning_rate": 6.303630363036304e-06,
+      "loss": 1.092,
+      "step": 3280
+    },
+    {
+      "epoch": 8.32,
+      "grad_norm": 3.719158411026001,
+      "learning_rate": 5.643564356435644e-06,
+      "loss": 1.1118,
+      "step": 3360
+    },
+    {
+      "epoch": 8.51,
+      "grad_norm": 4.2379374504089355,
+      "learning_rate": 4.9834983498349835e-06,
+      "loss": 1.1066,
+      "step": 3440
+    },
+    {
+      "epoch": 8.71,
+      "grad_norm": 4.96703577041626,
+      "learning_rate": 4.323432343234323e-06,
+      "loss": 1.1161,
+      "step": 3520
+    },
+    {
+      "epoch": 8.91,
+      "grad_norm": 9.020540237426758,
+      "learning_rate": 3.6633663366336635e-06,
+      "loss": 1.129,
+      "step": 3600
+    },
+    {
+      "epoch": 9.11,
+      "grad_norm": 3.624774217605591,
+      "learning_rate": 3.003300330033003e-06,
+      "loss": 1.097,
+      "step": 3680
+    },
+    {
+      "epoch": 9.31,
+      "grad_norm": 3.6332197189331055,
+      "learning_rate": 2.3432343234323434e-06,
+      "loss": 1.074,
+      "step": 3760
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 4.2010579109191895,
+      "learning_rate": 1.683168316831683e-06,
+      "loss": 1.0808,
+      "step": 3840
+    },
+    {
+      "epoch": 9.7,
+      "grad_norm": 3.434506416320801,
+      "learning_rate": 1.023102310231023e-06,
+      "loss": 1.0774,
+      "step": 3920
+    },
+    {
+      "epoch": 9.9,
+      "grad_norm": 4.213884353637695,
+      "learning_rate": 3.63036303630363e-07,
+      "loss": 1.1134,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 80,
+  "max_steps": 4040,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 9.936130988310528e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4040/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01b788f9e02180205714be9ffaf71e03e73d17a8fac23577a11f17d3dd94ef2
+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==4.38.1

runs/Mar06_21-38-30_r-theoracle-commodore2-9vrjlg93-0096a-fxgv1/events.out.tfevents.1709761111.r-theoracle-commodore2-9vrjlg93-0096a-fxgv1.98.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c04cf1eaff9e985491f1766572b6b6c16c750d0eb2df90b19061895b3d0d7fd
+size 15967

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
+size 17477553

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\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:c01b788f9e02180205714be9ffaf71e03e73d17a8fac23577a11f17d3dd94ef2
+size 4920

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "google/gemma-2b",
+    "project_name": "autotrain-lsmbq-gemma64",
+    "data_path": "autotrain-lsmbq-gemma64/autotrain-data",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "default",
+    "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": 10,
+    "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": "theoracle/autotrain-lsmbq-gemma64",
+    "username": "theoracle"
+}