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

Libraries

How to use diffusionfamily/diffullama with Transformers:

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

pipe = pipeline("text-generation", model="diffusionfamily/diffullama")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("diffusionfamily/diffullama")
model = AutoModelForCausalLM.from_pretrained("diffusionfamily/diffullama")

Inference
Local Apps Settings

vLLM

How to use diffusionfamily/diffullama with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/diffusionfamily/diffullama

SGLang

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

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

Sansa commited on Oct 21, 2024

Commit

0b399ea

verified ·

1 Parent(s): 01ea216

update readme

Browse files

Files changed (1) hide show

README.md +10 -25

README.md CHANGED Viewed

@@ -1,13 +1,18 @@
 ---
 library_name: transformers
-base_model: output/llama2-ddm
 tags:
 - llama-factory
 - full
-- generated_from_trainer
 model-index:
 - name: diffullama
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,36 +20,16 @@ should probably proofread and complete it, then remove this comment. -->
 # diffullama
-This model is a fine-tuned version of [output/llama2-ddm](https://huggingface.co/output/llama2-ddm) on an unknown dataset.
 ## 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: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3.0
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.1.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.19.1

 ---
 library_name: transformers
+base_model:
+- meta-llama/Llama-2-7b-hf
 tags:
 - llama-factory
 - full
+- diffusion
 model-index:
 - name: diffullama
   results: []
+license: mit
+datasets:
+- bigcode/starcoderdata
+- cerebras/SlimPajama-627B
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 # diffullama
+This model is a fine-tuned version of [llama2].
 ## Model description
+Details and model loading can be seen [https://github.com/HKUNLP/DiffuLLaMA](https://github.com/HKUNLP/DiffuLLaMA).
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.1.1+cu121
 - Datasets 2.21.0
+- Tokenizers 0.19.1