Instructions to use ClaudioItaly/Chronicle-Qwen2.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClaudioItaly/Chronicle-Qwen2.5-7B with Transformers:

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

pipe = pipeline("text-generation", model="ClaudioItaly/Chronicle-Qwen2.5-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ClaudioItaly/Chronicle-Qwen2.5-7B")
model = AutoModelForCausalLM.from_pretrained("ClaudioItaly/Chronicle-Qwen2.5-7B")
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

vLLM

How to use ClaudioItaly/Chronicle-Qwen2.5-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClaudioItaly/Chronicle-Qwen2.5-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClaudioItaly/Chronicle-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ClaudioItaly/Chronicle-Qwen2.5-7B

SGLang

How to use ClaudioItaly/Chronicle-Qwen2.5-7B 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 "ClaudioItaly/Chronicle-Qwen2.5-7B" \
    --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": "ClaudioItaly/Chronicle-Qwen2.5-7B",
		"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 "ClaudioItaly/Chronicle-Qwen2.5-7B" \
        --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": "ClaudioItaly/Chronicle-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ClaudioItaly/Chronicle-Qwen2.5-7B with Docker Model Runner:
```
docker model run hf.co/ClaudioItaly/Chronicle-Qwen2.5-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using nbeerbower/Dumpling-Qwen2.5-7B-1k-r32-2e-5 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  # Modello 1: Aggiunge la creatività generale al modello base (Dumpling)
  - model: ZeroXClem/Qwen2.5-7B-HomerCreative-Mix
    parameters:
      # density: Viene applicata la density globale specificata sotto
      weight: 0.75  # Peso più alto rispetto all'altro modello nella lista, per dare priorità alle sue caratteristiche (creatività) da aggiungere al base

  # Modello 2: Aggiunge le sue specifiche caratteristiche al modello base (Dumpling)
  - model: Cran-May/T.E-8.1
    parameters:
      # density: Viene applicata la density globale specificata sotto
      weight: 0.25  # Peso inferiore per le sue caratteristiche da aggiungere al base

  # NOTA IMPORTANTE: Il modello base (base_model) NON viene incluso nella lista 'models'
  # Nel metodo TIES, 'mergekit' calcola i "task vectors" come (modello_in_lista - base_model).
  # Questi vettori di differenza vengono poi potati, normalizzati (se normalize: true) e sommati pesati,
  # e infine aggiunti al base_model.
  # Quindi, nbeerbower/Dumpling-Qwen2.5-7B-1k-r32-2e-5 è il punto di partenza, e aggiungiamo un mix delle differenze degli altri due modelli rispetto a Dumpling.

merge_method: ties
base_model: nbeerbower/Dumpling-Qwen2.5-7B-1k-r32-2e-5 # Nuovo modello base

parameters:
  density: 0.7      # Percentuale di parametri non nulli da mantenere nei task vectors di *ciascuno* dei modelli nella lista 'models'.
  # mask_threshold: 0.02 # Rimosso, non si applica a TIES.
  normalize: true   # Normalizza i task vectors potati prima di applicare i pesi. Raccomandato con TIES multi-modello.
  int8_mask: true   # Opzione utile per risparmiare memoria.
dtype: bfloat16     # Corrisponde al dtype del nuovo modello base.