Upload 12 files

README.md

@@ -1,3 +1,207 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: mistralai/Mistral-7B-Instruct-v0.1
 ---
+
+# 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]
+- **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 Data 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 Data 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]
+
+
+## Training procedure
+
+
+### Framework versions
+
+
+- PEFT 0.6.0

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "out_proj",
+    "Wqkv",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff8dc8f46625eeb4ba1f093583cd724ecf118f83821f77ede4bb766481385d92
+size 151040461

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6dc7473f7056237014c13b746df5b0396040c03df1e6ef371d71024769603c4
+size 302068997

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb31441f4fc8ac13206aeff39c6389be1efea0bcdc435b5dc5fb888949c9057
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ab251bfd3a133e9874cb431591e1a0fc1d72e2da409f91ee54404c884712a6
+size 627

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 +1,41 @@
+{
+  "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": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,163 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.996875,
+  "eval_steps": 500,
+  "global_step": 1599,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.896907216494846e-05,
+      "loss": 1.5529,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 0.9276,
+      "step": 128
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.072164948453609e-05,
+      "loss": 0.879,
+      "step": 192
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.65979381443299e-05,
+      "loss": 0.8731,
+      "step": 256
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.247422680412371e-05,
+      "loss": 0.8242,
+      "step": 320
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.835051546391753e-05,
+      "loss": 0.7293,
+      "step": 384
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 0.7194,
+      "step": 448
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 7.010309278350515e-05,
+      "loss": 0.6864,
+      "step": 512
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 6.597938144329897e-05,
+      "loss": 0.7096,
+      "step": 576
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.185567010309279e-05,
+      "loss": 0.6913,
+      "step": 640
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 5.7731958762886594e-05,
+      "loss": 0.5724,
+      "step": 704
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 0.5465,
+      "step": 768
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.948453608247423e-05,
+      "loss": 0.5307,
+      "step": 832
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 4.536082474226804e-05,
+      "loss": 0.5446,
+      "step": 896
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.1237113402061855e-05,
+      "loss": 0.5501,
+      "step": 960
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.7113402061855674e-05,
+      "loss": 0.4308,
+      "step": 1024
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 0.4082,
+      "step": 1088
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2.8865979381443297e-05,
+      "loss": 0.4158,
+      "step": 1152
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 2.4742268041237116e-05,
+      "loss": 0.4281,
+      "step": 1216
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.0618556701030927e-05,
+      "loss": 0.4065,
+      "step": 1280
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 1.6494845360824743e-05,
+      "loss": 0.3311,
+      "step": 1344
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 1.2371134020618558e-05,
+      "loss": 0.3239,
+      "step": 1408
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 8.247422680412371e-06,
+      "loss": 0.322,
+      "step": 1472
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 4.123711340206186e-06,
+      "loss": 0.3261,
+      "step": 1536
+    }
+  ],
+  "logging_steps": 64,
+  "max_steps": 1600,
+  "num_train_epochs": 5,
+  "save_steps": 1599,
+  "total_flos": 1.2482695900296806e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac66b30cd9d21f86519c40ad60addc9e7ec40ab7a13109f5392f7aee323e1c2
+size 4091