Instructions to use deqing/llama-600M-v4-isolate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deqing/llama-600M-v4-isolate with Transformers:

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

pipe = pipeline("text-generation", model="deqing/llama-600M-v4-isolate")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deqing/llama-600M-v4-isolate")
model = AutoModelForCausalLM.from_pretrained("deqing/llama-600M-v4-isolate")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deqing/llama-600M-v4-isolate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deqing/llama-600M-v4-isolate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deqing/llama-600M-v4-isolate",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deqing/llama-600M-v4-isolate

SGLang

How to use deqing/llama-600M-v4-isolate 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 "deqing/llama-600M-v4-isolate" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deqing/llama-600M-v4-isolate",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "deqing/llama-600M-v4-isolate" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deqing/llama-600M-v4-isolate",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deqing/llama-600M-v4-isolate with Docker Model Runner:
```
docker model run hf.co/deqing/llama-600M-v4-isolate
```

llama-600M-v4-isolate / README.md

deqing

Model save

d6e4349 verified 3 months ago

preview code

raw

history blame contribute delete

1.45 kB

	---
	library_name: transformers
	base_model: llama_600M_config.json
	tags:
	- generated_from_trainer
	model-index:
	- name: llama-600M-v4-isolate
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# llama-600M-v4-isolate

	This model is a fine-tuned version of [llama_600M_config.json](https://huggingface.co/llama_600M_config.json) on an unknown dataset.
	It achieves the following results on the evaluation set:
	- Loss: 2.7799
	- Num Input Tokens Seen: 9437184000

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.0003
	- train_batch_size: 32
	- eval_batch_size: 32
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 2
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 512
	- total_eval_batch_size: 64
	- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_steps: 500
	- num_epochs: 1

	### Training results



	### Framework versions

	- Transformers 5.3.0
	- Pytorch 2.10.0+cu128
	- Datasets 4.7.0
	- Tokenizers 0.22.2