Upload folder using huggingface_hub

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 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa85fe3e5d0eaa29d9441b4002b983c902ad694c8fc4bb50c832d0d22559f75e
+size 92317600

checkpoint-100/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.2
+---
+
+# 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 0.7.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "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": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa85fe3e5d0eaa29d9441b4002b983c902ad694c8fc4bb50c832d0d22559f75e
+size 92317600

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f0235db080282cc942d13e66453e0df264e4a4c7ab1e689234c7914cd48552
+size 184818874

checkpoint-100/pytorch_model.bin

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

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273be72067560ba36b3fa3df1ac4e9d765648d872d3613df97e851a3650e6034
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
+size 1064

checkpoint-100/special_tokens_map.json

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

checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,621 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2e-05,
+      "loss": 2.3971,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.461,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 6e-05,
+      "loss": 2.5204,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 2.1248,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.0001,
+      "loss": 1.9833,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00012,
+      "loss": 2.1376,
+      "step": 6
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.00014,
+      "loss": 1.8588,
+      "step": 7
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00016,
+      "loss": 1.7741,
+      "step": 8
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 0.00018,
+      "loss": 1.6101,
+      "step": 9
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0002,
+      "loss": 1.602,
+      "step": 10
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 0.00019777777777777778,
+      "loss": 1.3506,
+      "step": 11
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.00019555555555555556,
+      "loss": 1.3243,
+      "step": 12
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00019333333333333333,
+      "loss": 1.1528,
+      "step": 13
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00019111111111111114,
+      "loss": 1.0344,
+      "step": 14
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 0.00018888888888888888,
+      "loss": 0.9344,
+      "step": 15
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.866,
+      "step": 16
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 0.00018444444444444446,
+      "loss": 0.6751,
+      "step": 17
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 0.00018222222222222224,
+      "loss": 0.66,
+      "step": 18
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 0.00018,
+      "loss": 0.5083,
+      "step": 19
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 0.4227,
+      "step": 20
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 0.00017555555555555556,
+      "loss": 0.3149,
+      "step": 21
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.2655,
+      "step": 22
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 0.0001711111111111111,
+      "loss": 0.1734,
+      "step": 23
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.00016888888888888889,
+      "loss": 0.1669,
+      "step": 24
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 0.1155,
+      "step": 25
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 0.00016444444444444444,
+      "loss": 0.0967,
+      "step": 26
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 0.00016222222222222224,
+      "loss": 0.0663,
+      "step": 27
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.00016,
+      "loss": 0.0794,
+      "step": 28
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 0.0001577777777777778,
+      "loss": 0.0642,
+      "step": 29
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 0.0495,
+      "step": 30
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 0.00015333333333333334,
+      "loss": 0.0395,
+      "step": 31
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.0001511111111111111,
+      "loss": 0.0731,
+      "step": 32
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 0.0001488888888888889,
+      "loss": 0.0458,
+      "step": 33
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 0.00014666666666666666,
+      "loss": 0.0499,
+      "step": 34
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 0.00014444444444444444,
+      "loss": 0.0345,
+      "step": 35
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.00014222222222222224,
+      "loss": 0.0463,
+      "step": 36
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 0.00014,
+      "loss": 0.0333,
+      "step": 37
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 0.0001377777777777778,
+      "loss": 0.0361,
+      "step": 38
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 0.00013555555555555556,
+      "loss": 0.0315,
+      "step": 39
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.0322,
+      "step": 40
+    },
+    {
+      "epoch": 20.5,
+      "learning_rate": 0.00013111111111111111,
+      "loss": 0.0281,
+      "step": 41
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 0.00012888888888888892,
+      "loss": 0.0243,
+      "step": 42
+    },
+    {
+      "epoch": 21.5,
+      "learning_rate": 0.00012666666666666666,
+      "loss": 0.0181,
+      "step": 43
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 0.00012444444444444444,
+      "loss": 0.0277,
+      "step": 44
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 0.00012222222222222224,
+      "loss": 0.0196,
+      "step": 45
+    },
+    {
+      "epoch": 23.0,
+      "learning_rate": 0.00012,
+      "loss": 0.0257,
+      "step": 46
+    },
+    {
+      "epoch": 23.5,
+      "learning_rate": 0.00011777777777777779,
+      "loss": 0.0153,
+      "step": 47
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 0.00011555555555555555,
+      "loss": 0.0252,
+      "step": 48
+    },
+    {
+      "epoch": 24.5,
+      "learning_rate": 0.00011333333333333334,
+      "loss": 0.0134,
+      "step": 49
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 0.0256,
+      "step": 50
+    },
+    {
+      "epoch": 25.5,
+      "learning_rate": 0.00010888888888888889,
+      "loss": 0.025,
+      "step": 51
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.0137,
+      "step": 52
+    },
+    {
+      "epoch": 26.5,
+      "learning_rate": 0.00010444444444444445,
+      "loss": 0.0195,
+      "step": 53
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.00010222222222222222,
+      "loss": 0.0179,
+      "step": 54
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 0.0001,
+      "loss": 0.0178,
+      "step": 55
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 9.777777777777778e-05,
+      "loss": 0.0181,
+      "step": 56
+    },
+    {
+      "epoch": 28.5,
+      "learning_rate": 9.555555555555557e-05,
+      "loss": 0.013,
+      "step": 57
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.0226,
+      "step": 58
+    },
+    {
+      "epoch": 29.5,
+      "learning_rate": 9.111111111111112e-05,
+      "loss": 0.0223,
+      "step": 59
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 0.0126,
+      "step": 60
+    },
+    {
+      "epoch": 30.5,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.0173,
+      "step": 61
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 8.444444444444444e-05,
+      "loss": 0.0168,
+      "step": 62
+    },
+    {
+      "epoch": 31.5,
+      "learning_rate": 8.222222222222222e-05,
+      "loss": 0.0158,
+      "step": 63
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 8e-05,
+      "loss": 0.0176,
+      "step": 64
+    },
+    {
+      "epoch": 32.5,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 0.0214,
+      "step": 65
+    },
+    {
+      "epoch": 33.0,
+      "learning_rate": 7.555555555555556e-05,
+      "loss": 0.0117,
+      "step": 66
+    },
+    {
+      "epoch": 33.5,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.0215,
+      "step": 67
+    },
+    {
+      "epoch": 34.0,
+      "learning_rate": 7.111111111111112e-05,
+      "loss": 0.0108,
+      "step": 68
+    },
+    {
+      "epoch": 34.5,
+      "learning_rate": 6.88888888888889e-05,
+      "loss": 0.0109,
+      "step": 69
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.0206,
+      "step": 70
+    },
+    {
+      "epoch": 35.5,
+      "learning_rate": 6.444444444444446e-05,
+      "loss": 0.0158,
+      "step": 71
+    },
+    {
+      "epoch": 36.0,
+      "learning_rate": 6.222222222222222e-05,
+      "loss": 0.0152,
+      "step": 72
+    },
+    {
+      "epoch": 36.5,
+      "learning_rate": 6e-05,
+      "loss": 0.0089,
+      "step": 73
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 5.7777777777777776e-05,
+      "loss": 0.0215,
+      "step": 74
+    },
+    {
+      "epoch": 37.5,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 0.0147,
+      "step": 75
+    },
+    {
+      "epoch": 38.0,
+      "learning_rate": 5.333333333333333e-05,
+      "loss": 0.0148,
+      "step": 76
+    },
+    {
+      "epoch": 38.5,
+      "learning_rate": 5.111111111111111e-05,
+      "loss": 0.0144,
+      "step": 77
+    },
+    {
+      "epoch": 39.0,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.0145,
+      "step": 78
+    },
+    {
+      "epoch": 39.5,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.0142,
+      "step": 79
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.0142,
+      "step": 80
+    },
+    {
+      "epoch": 40.5,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 0.0137,
+      "step": 81
+    },
+    {
+      "epoch": 41.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0138,
+      "step": 82
+    },
+    {
+      "epoch": 41.5,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.0146,
+      "step": 83
+    },
+    {
+      "epoch": 42.0,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.0129,
+      "step": 84
+    },
+    {
+      "epoch": 42.5,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.0078,
+      "step": 85
+    },
+    {
+      "epoch": 43.0,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 0.0186,
+      "step": 86
+    },
+    {
+      "epoch": 43.5,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 0.0075,
+      "step": 87
+    },
+    {
+      "epoch": 44.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.0186,
+      "step": 88
+    },
+    {
+      "epoch": 44.5,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 0.0129,
+      "step": 89
+    },
+    {
+      "epoch": 45.0,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0128,
+      "step": 90
+    },
+    {
+      "epoch": 45.5,
+      "learning_rate": 2e-05,
+      "loss": 0.0187,
+      "step": 91
+    },
+    {
+      "epoch": 46.0,
+      "learning_rate": 1.777777777777778e-05,
+      "loss": 0.0065,
+      "step": 92
+    },
+    {
+      "epoch": 46.5,
+      "learning_rate": 1.5555555555555555e-05,
+      "loss": 0.0128,
+      "step": 93
+    },
+    {
+      "epoch": 47.0,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.0126,
+      "step": 94
+    },
+    {
+      "epoch": 47.5,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.0123,
+      "step": 95
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 8.88888888888889e-06,
+      "loss": 0.0128,
+      "step": 96
+    },
+    {
+      "epoch": 48.5,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.0124,
+      "step": 97
+    },
+    {
+      "epoch": 49.0,
+      "learning_rate": 4.444444444444445e-06,
+      "loss": 0.0124,
+      "step": 98
+    },
+    {
+      "epoch": 49.5,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 0.0124,
+      "step": 99
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0,
+      "loss": 0.0123,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "total_flos": 1.75318518202368e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083fbf13af3ea247886ec79dad9f260ba26c206249619be7661ee7e3740dcb62
+size 4728

handler.py

@@ -0,0 +1,31 @@
+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(base_model_path, trust_remote_code=True)
+        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==0.7.1
+transformers==4.36.1

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% 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'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083fbf13af3ea247886ec79dad9f260ba26c206249619be7661ee7e3740dcb62
+size 4728

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "mistralai/Mistral-7B-Instruct-v0.2",
+    "project_name": "my_autotrain_llm_3",
+    "data_path": "data/",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": false,
+    "block_size": 1024,
+    "model_max_length": 1024,
+    "padding": null,
+    "trainer": "default",
+    "use_flash_attention_2": false,
+    "log": "wandb",
+    "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": 0.0002,
+    "epochs": 50,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "apply_chat_template": false,
+    "quantization": "int4",
+    "target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj",
+    "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": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "push_to_hub": true,
+    "repo_id": "karthikrathod/llm_repo_v8_10e",
+    "username": null
+}