Instructions to use DorinSht/ShareGPT_llama2_68M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DorinSht/ShareGPT_llama2_68M with Transformers:

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

pipe = pipeline("text-generation", model="DorinSht/ShareGPT_llama2_68M")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DorinSht/ShareGPT_llama2_68M")
model = AutoModelForCausalLM.from_pretrained("DorinSht/ShareGPT_llama2_68M")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DorinSht/ShareGPT_llama2_68M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DorinSht/ShareGPT_llama2_68M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DorinSht/ShareGPT_llama2_68M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DorinSht/ShareGPT_llama2_68M

SGLang

How to use DorinSht/ShareGPT_llama2_68M 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 "DorinSht/ShareGPT_llama2_68M" \
    --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": "DorinSht/ShareGPT_llama2_68M",
		"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 "DorinSht/ShareGPT_llama2_68M" \
        --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": "DorinSht/ShareGPT_llama2_68M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DorinSht/ShareGPT_llama2_68M with Docker Model Runner:
```
docker model run hf.co/DorinSht/ShareGPT_llama2_68M
```

ShareGPT_llama2_68M

This model is a fine-tuned version of JackFram/llama-68m on the anon8231489123/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json dataset. It achieves the following results on the evaluation set:

Loss: 2.3592
Accuracy: 0.5813

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: 0.0001
train_batch_size: 24
eval_batch_size: 48
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.406	0.2644	1000	3.2345	0.5035
2.8119	0.5288	2000	2.8214	0.5365
2.607	0.7932	3000	2.6572	0.5498
2.4734	1.0576	4000	2.5736	0.5582
2.4335	1.3221	5000	2.5336	0.5617
2.3858	1.5865	6000	2.4896	0.5663
2.374	1.8509	7000	2.4711	0.5681
2.3044	2.1153	8000	2.4485	0.5702
2.2873	2.3797	9000	2.4132	0.5747
2.2669	2.6441	10000	2.3879	0.5778
2.2463	2.9085	11000	2.3636	0.5808

Framework versions

Transformers 4.41.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 7

Safetensors

Model size

68M params

Tensor type

F32

Model tree for DorinSht/ShareGPT_llama2_68M

Base model

JackFram/llama-68m

Finetuned

(19)

this model