Upload folder using huggingface_hub

README.md

@@ -0,0 +1,207 @@
+---
+base_model: mistralai/Devstral-Small-2507
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Devstral-Small-2507
+- lora
+- transformers
+---
+
+# 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 0.18.0

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Devstral-Small-2507",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df7d1fd26894eaaae571ee8b3010920bf2d7e1aa2dc73b0e7d235669b72fbaf
+size 1478568312

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758e64e3c09db3a0126d611cc34f3f9a7609b5ddbe644030e2c4230ebce8fcd4
+size 2957458227

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07bb73f0b8528f8a9b9a5d4d2a83cf690534a6dc53c6739e72f270206df51240
+size 14917

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f04dc713ef6d607e37b78627f393d032fbff0b4f1fd8a3870d2d25aaf2d86b
+size 14917

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c7cd5b61053d7eb0793976bbfe397a78580b47c769cc60922f74c74b783d22
+size 1465

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 24.712718963623047,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3557,
+      "step": 5
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 6.129093170166016,
+      "learning_rate": 4.5e-06,
+      "loss": 1.0059,
+      "step": 10
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 1.9026240110397339,
+      "learning_rate": 7.000000000000001e-06,
+      "loss": 0.7361,
+      "step": 15
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.9946033358573914,
+      "learning_rate": 9.5e-06,
+      "loss": 0.5916,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.00466787815094,
+      "learning_rate": 1.2e-05,
+      "loss": 0.5726,
+      "step": 25
+    },
+    {
+      "epoch": 1.2040816326530612,
+      "grad_norm": 1.4974271059036255,
+      "learning_rate": 1.45e-05,
+      "loss": 0.4539,
+      "step": 30
+    },
+    {
+      "epoch": 1.4081632653061225,
+      "grad_norm": 0.9463223814964294,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 0.418,
+      "step": 35
+    },
+    {
+      "epoch": 1.6122448979591837,
+      "grad_norm": 0.6594650149345398,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 0.3429,
+      "step": 40
+    },
+    {
+      "epoch": 1.816326530612245,
+      "grad_norm": 0.8124538064002991,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 0.3625,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0463100671768188,
+      "learning_rate": 2.45e-05,
+      "loss": 0.279,
+      "step": 50
+    },
+    {
+      "epoch": 2.204081632653061,
+      "grad_norm": 0.7678775191307068,
+      "learning_rate": 2.7000000000000002e-05,
+      "loss": 0.2144,
+      "step": 55
+    },
+    {
+      "epoch": 2.4081632653061225,
+      "grad_norm": 0.6989904046058655,
+      "learning_rate": 2.95e-05,
+      "loss": 0.2167,
+      "step": 60
+    },
+    {
+      "epoch": 2.612244897959184,
+      "grad_norm": 0.7240927815437317,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.189,
+      "step": 65
+    },
+    {
+      "epoch": 2.816326530612245,
+      "grad_norm": 0.6139882802963257,
+      "learning_rate": 3.45e-05,
+      "loss": 0.2136,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0273910760879517,
+      "learning_rate": 3.7e-05,
+      "loss": 0.219,
+      "step": 75
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.725621273151406e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6371d60b718e7ba913f956b7fa61f0e10594c0b74f74dcbdfe48a148c6c4513c
+size 5201