Instructions to use mindfossil/telecom-intelligence-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mindfossil/telecom-intelligence-model with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mindfossil/telecom-intelligence-model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mindfossil/telecom-intelligence-model")
model = AutoModelForCausalLM.from_pretrained("mindfossil/telecom-intelligence-model", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mindfossil/telecom-intelligence-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mindfossil/telecom-intelligence-model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mindfossil/telecom-intelligence-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mindfossil/telecom-intelligence-model

SGLang

How to use mindfossil/telecom-intelligence-model with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mindfossil/telecom-intelligence-model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mindfossil/telecom-intelligence-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mindfossil/telecom-intelligence-model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mindfossil/telecom-intelligence-model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use mindfossil/telecom-intelligence-model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mindfossil/telecom-intelligence-model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mindfossil/telecom-intelligence-model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mindfossil/telecom-intelligence-model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="mindfossil/telecom-intelligence-model",
    max_seq_length=2048,
)

Docker Model Runner
How to use mindfossil/telecom-intelligence-model with Docker Model Runner:
```
docker model run hf.co/mindfossil/telecom-intelligence-model
```

telecom-intelligence-model

File size: 1,654 Bytes

58c50d6

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.180859375,
      "epoch": 0.37037037037037035,
      "grad_norm": 1.9087318181991577,
      "learning_rate": 0.00019886154122075343,
      "loss": 1.3855,
      "mean_token_accuracy": 0.709491191804409,
      "num_tokens": 20480.0,
      "step": 10
    },
    {
      "entropy": 0.77197265625,
      "epoch": 0.7407407407407407,
      "grad_norm": 1.5744595527648926,
      "learning_rate": 0.00018990881137654258,
      "loss": 0.8126,
      "mean_token_accuracy": 0.8044520571827889,
      "num_tokens": 40960.0,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_entropy": 0.666015625,
      "eval_loss": 0.664973795413971,
      "eval_mean_token_accuracy": 0.8258317112922668,
      "eval_num_tokens": 55296.0,
      "eval_runtime": 104.8748,
      "eval_samples_per_second": 0.114,
      "eval_steps_per_second": 0.019,
      "step": 27
    }
  ],
  "logging_steps": 10,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2374105735102464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}