Upload 9 files

README.md

@@ -1,3 +1,202 @@
----
-license: mit
----
+---
+base_model: dicta-il/dictalm2.0-instruct
+library_name: peft
+---
+
+# 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 0.13.2

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MistralBiModel",
+    "parent_library": "llm2vec.models.bidirectional_mistral"
+  },
+  "base_model_name_or_path": "dicta-il/dictalm2.0-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "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",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4021eb15f499786741a4da0022362452fc0fa9261cd9a271b94190aa845b5b
+size 167829552

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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
+  },
+  "mask_token": "_",
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+    }
+  },
+  "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]\n' }}{% 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,
+  "mask_token": "_",
+  "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": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.4050222762251924,
+    "total_flos": 7.03593355149312e+17,
+    "train_loss": 5.223868896484375,
+    "train_runtime": 10418.308,
+    "train_samples": 78993,
+    "train_samples_per_second": 22.746,
+    "train_steps_per_second": 0.711
+}

trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4050222762251924,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04050222762251924,
+      "eval_accuracy": 0.07313909615825066,
+      "eval_loss": 5.535554885864258,
+      "eval_runtime": 288.6011,
+      "eval_samples_per_second": 14.075,
+      "eval_steps_per_second": 0.44,
+      "step": 100
+    },
+    {
+      "epoch": 0.08100445524503848,
+      "eval_accuracy": 0.09321176989128148,
+      "eval_loss": 5.312517166137695,
+      "eval_runtime": 289.0997,
+      "eval_samples_per_second": 14.051,
+      "eval_steps_per_second": 0.439,
+      "step": 200
+    },
+    {
+      "epoch": 0.12150668286755771,
+      "eval_accuracy": 0.1025266924717497,
+      "eval_loss": 5.209850788116455,
+      "eval_runtime": 288.9641,
+      "eval_samples_per_second": 14.057,
+      "eval_steps_per_second": 0.44,
+      "step": 300
+    },
+    {
+      "epoch": 0.16200891049007696,
+      "eval_accuracy": 0.10690876214872297,
+      "eval_loss": 5.157820224761963,
+      "eval_runtime": 288.9416,
+      "eval_samples_per_second": 14.058,
+      "eval_steps_per_second": 0.44,
+      "step": 400
+    },
+    {
+      "epoch": 0.2025111381125962,
+      "grad_norm": 4.206667900085449,
+      "learning_rate": 4.6624814364790066e-05,
+      "loss": 5.3676,
+      "step": 500
+    },
+    {
+      "epoch": 0.2025111381125962,
+      "eval_accuracy": 0.11018071094865264,
+      "eval_loss": 5.133289337158203,
+      "eval_runtime": 288.702,
+      "eval_samples_per_second": 14.07,
+      "eval_steps_per_second": 0.44,
+      "step": 500
+    },
+    {
+      "epoch": 0.24301336573511542,
+      "eval_accuracy": 0.1130116481766369,
+      "eval_loss": 5.102772235870361,
+      "eval_runtime": 288.9586,
+      "eval_samples_per_second": 14.057,
+      "eval_steps_per_second": 0.44,
+      "step": 600
+    },
+    {
+      "epoch": 0.28351559335763465,
+      "eval_accuracy": 0.11700033155499291,
+      "eval_loss": 5.068767070770264,
+      "eval_runtime": 288.67,
+      "eval_samples_per_second": 14.071,
+      "eval_steps_per_second": 0.44,
+      "step": 700
+    },
+    {
+      "epoch": 0.3240178209801539,
+      "eval_accuracy": 0.1189196062267089,
+      "eval_loss": 5.049363136291504,
+      "eval_runtime": 288.7628,
+      "eval_samples_per_second": 14.067,
+      "eval_steps_per_second": 0.44,
+      "step": 800
+    },
+    {
+      "epoch": 0.3645200486026732,
+      "eval_accuracy": 0.12067047317065237,
+      "eval_loss": 5.0373969078063965,
+      "eval_runtime": 288.4915,
+      "eval_samples_per_second": 14.08,
+      "eval_steps_per_second": 0.44,
+      "step": 900
+    },
+    {
+      "epoch": 0.4050222762251924,
+      "grad_norm": 2.745899200439453,
+      "learning_rate": 4.324962872958013e-05,
+      "loss": 5.0801,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4050222762251924,
+      "eval_accuracy": 0.12251942264285288,
+      "eval_loss": 5.018136024475098,
+      "eval_runtime": 288.8733,
+      "eval_samples_per_second": 14.062,
+      "eval_steps_per_second": 0.44,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4050222762251924,
+      "step": 1000,
+      "total_flos": 7.03593355149312e+17,
+      "train_loss": 5.223868896484375,
+      "train_runtime": 10418.308,
+      "train_samples_per_second": 22.746,
+      "train_steps_per_second": 0.711
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7407,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "total_flos": 7.03593355149312e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d15de8fa70d60d867ed4615c93a812f277a713e06245b0e12f889a8603b6ebe
+size 4984