README.md

---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
base_model:
- HuggingFaceTB/SmolLM-135M-Instruct
datasets: []
languages:
- en
library_name: transformers
metrics: []
pipeline_tag: text-generation
tags: []

---

# Model Card for ldp72/Test-SmolLM-Marcel-codecarbon

<!-- Provide a quick summary of what the model is/does. -->

This model was finetuned by performing instruct tuning on Telco domain datatsets.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Developed by:** Orange
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** English
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** HuggingFaceTB/SmolLM-135M-Instruct
- **Date [optional]:** 2025-08-28 16:18:47

### 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. -->

This model can be used with the `transformers` library using `pipeline` abstraction as follows:

```python
import torch
from transformers import pipeline

model_id = "ldp72/Test-SmolLM-Marcel-codecarbon"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are chatbot specialized on Telco domain."},
{"role": "user", "content": "Can you give a sample of your specialized knowledge?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```

### 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

This model was finetuned with [Orange internal fine tuning tools](https://gitlab.tech.orange/NEPAL/knowledge/orangelm/lm-adaptation/)  with the Docker Image tagged `0.1.2` in the [registry](https://gitlab.tech.orange/NEPAL/knowledge/orangelm/lm-adaptation/container_registry/84664) and the following configuration file:

```yaml
data:
dataset_name:
train:
-   path: telco-lm/arxiv-abstract-generation-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-dsp.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-networkengineering.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-security.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-3gpp-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-5gamericas-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-huawei-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-itu-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-mef-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-ngmn-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-rfc-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/teleqna-mcqa-cot-telco-instructions
revision: legacy
-   path: telco-lm/tii-huawei-qa-open-qa-telco-instructions
revision: legacy
validation_abstract_generation:
-   path: telco-lm/arxiv-abstract-generation-telco-instructions
revision: legacy
split: validation
validation_general:
-   path: telco-lm/slim-orca-multi-task-general-instructions
revision: legacy
split: validation
validation_synthetic:
-   path: telco-lm/synthetic-dsp.stackexchange.com-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-security.stackexchange.com-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-networkengineering.stackexchange.com-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-rfc-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-3gpp-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-5gamericas-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-itu-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-mef-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-huawei-multi-task-telco-instructions
revision: legacy
split: validation
-   path: telco-lm/synthetic-technical-ngmn-multi-task-telco-instructions
revision: legacy
split: validation
validation_telco_qa:
-   path: telco-lm/tii-huawei-qa-open-qa-telco-instructions
revision: legacy
split: validation
validation_telco_qcm:
-   path: telco-lm/teleqna-mcqa-cot-telco-instructions
revision: legacy
split: validation
debug: true
implementation_name: instructions
description:
contributors:
-   email: loic.fosse@orange.com
first_name: Loïc
last_name: Fosse
-   email: lionel.delphinpoulat@orange.com
first_name: Lionel
last_name: Delphin-Poulat
-   email: ismael.rousseau@orange.com
first_name: Ismaël
last_name: Rousseau
domain: Telco
languages:
- en
model_name: ldp72/Test-SmolLM-Marcel-codecarbon
image:
version: 0.1.2
model:
attn_implementation: flash_attention_2
chat_template_tokenizer: HuggingFaceTB/SmolLM-135M-Instruct
model_name_or_path: HuggingFaceTB/SmolLM-135M-Instruct
trust_remote_code: true
training:
bf16: true
dataloader_num_workers: 4
dataloader_persistent_workers: true
dataloader_pin_memory: true
dataloader_prefetch_factor: 2
deepspeed: /config/zero3.json
disable_tqdm: true
eval_accumulation_steps: 1
eval_steps: 10
eval_strategy: steps
fp16: false
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
learning_rate: 2.0e-05
log_level: debug
logging_dir: /outputs/Telco-SmolLM-135-Instruct-it-test-codecarbon-process-push/logs
logging_steps: 10
lr_scheduler_type: cosine
max_grad_norm: 1.0
max_steps: -1
num_train_epochs: 2
optim: paged_adamw_32bit
output_dir: /outputs/Telco-SmolLM-135-Instruct-it-test-codecarbon-process-push
per_device_eval_batch_size: 2
per_device_train_batch_size: 2
push_to_hub: false
report_to: tensorboard
save_steps: 0
save_strategy: epoch
save_total_limit: 1
seed: 42
torch_compile: false
training_type: instruct-tuning
use_liger_kernel: false
warmup_ratio: 0.05
weight_decay: 0.1
```

The model was trained on 1 gpus with at least 40GB on each gpu.

The model was trained using [deepspeed](https://www.deepspeed.ai/) with the following configuration file:

```json
{
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 3,
"offload_optimizer": {
"device": "cpu",
"pin_memory": true
},
"offload_param": {
"device": "cpu",
"pin_memory": true
},
"overlap_comm": true,
"contiguous_gradients": true,
"sub_group_size": "1e9",
"reduce_bucket_size": "auto",
"stage3_prefetch_bucket_size": "auto",
"stage3_param_persistence_threshold": "auto",
"stage3_max_live_parameters": "1e9",
"stage3_max_reuse_distance": "1e9",
"stage3_gather_16bit_weights_on_model_save": true
},
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"steps_per_print": 2000,
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"wall_clock_breakdown": false
}
```

### 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. -->

This model was trained on the following datasets:

```yaml
-   path: telco-lm/arxiv-abstract-generation-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-dsp.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-networkengineering.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-security.stackexchange.com-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-3gpp-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-5gamericas-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-huawei-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-itu-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-mef-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-ngmn-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/synthetic-technical-rfc-multi-task-telco-instructions
revision: legacy
-   path: telco-lm/teleqna-mcqa-cot-telco-instructions
revision: legacy
-   path: telco-lm/tii-huawei-qa-open-qa-telco-instructions
revision: legacy
```

### 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

<!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

- **Training regime:** This model was trained with the following hyperparameters for `SFTTrainer`,other parameters were set as default:

```yaml
bf16: true
dataloader_num_workers: 4
dataloader_persistent_workers: true
dataloader_pin_memory: true
dataloader_prefetch_factor: 2
deepspeed: /config/zero3.json
disable_tqdm: true
eval_accumulation_steps: 1
eval_steps: 10
eval_strategy: steps
fp16: false
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
learning_rate: 2.0e-05
log_level: debug
logging_dir: /outputs/Telco-SmolLM-135-Instruct-it-test-codecarbon-process-push/logs
logging_steps: 10
lr_scheduler_type: cosine
max_grad_norm: 1.0
max_steps: -1
num_train_epochs: 2
optim: paged_adamw_32bit
output_dir: /outputs/Telco-SmolLM-135-Instruct-it-test-codecarbon-process-push
per_device_eval_batch_size: 2
per_device_train_batch_size: 2
push_to_hub: false
report_to: tensorboard
save_steps: 0
save_strategy: epoch
save_total_limit: 1
seed: 42
torch_compile: false
use_liger_kernel: false
warmup_ratio: 0.05
weight_decay: 0.1
```

#### 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:** CPUs: AMD EPYC 7282 16-Core Processor; GPUs: 1 x NVIDIA A100-PCIE-40GB
- **Hours used:** 0:10:44
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:**  0.00089 kg CO2eq, detailed emissions can be found in [`emissions.csv`](./emissions.csv) (emissions were computed using [`codecarbon`](https://codecarbon.io/))

## 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

Thanks to [Loïc Fosse](mailto:loic.fosse@orange.com), [Lionel Delphin-Poulat](mailto:lionel.delphinpoulat@orange.com), [Ismaël Rousseau](mailto:ismael.rousseau@orange.com) for adding this model.