Instructions to use semran1/baseline_model_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use semran1/baseline_model_1B with Transformers:

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

pipe = pipeline("text-generation", model="semran1/baseline_model_1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("semran1/baseline_model_1B")
model = AutoModelForCausalLM.from_pretrained("semran1/baseline_model_1B")
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 semran1/baseline_model_1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "semran1/baseline_model_1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "semran1/baseline_model_1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/semran1/baseline_model_1B

SGLang

How to use semran1/baseline_model_1B 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 "semran1/baseline_model_1B" \
    --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": "semran1/baseline_model_1B",
		"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 "semran1/baseline_model_1B" \
        --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": "semran1/baseline_model_1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use semran1/baseline_model_1B with Docker Model Runner:
```
docker model run hf.co/semran1/baseline_model_1B
```

baseline_model_1B

File size: 1,163 Bytes

e61b0c4

{"_name_or_path": "semran1/l3.2-3b-63-deg2", "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "aux_loss_type": "mseloss", "bos_token_id": 128000, "check_data_cls_loss": false, "del_layers": [], "eos_token_id": 128009, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8192, "kl_temperature": 10.0, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": 128004, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 32.0, "type": "dynamic"}, "rope_theta": 500000.0, "student_attn_from_scratch": false, "target_hidden_size": 1536, "target_rms_norm_eps": 1e-05, "tie_word_emb_proj": 1, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.42.0", "unsloth_fixed": true, "use_additional_align": false, "use_all_attn": 1, "use_attn_map": false, "use_aux_loss": true, "use_cache": true, "use_in_out_mlp": false, "use_logits_loss": true, "use_ntp_loss": true, "use_std_like_attn": false, "vocab_size": 128256}