Instructions to use ZainAli60/tuned_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ZainAli60/tuned_model with Transformers:

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

pipe = pipeline("text-generation", model="ZainAli60/tuned_model", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ZainAli60/tuned_model", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("ZainAli60/tuned_model", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ZainAli60/tuned_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ZainAli60/tuned_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ZainAli60/tuned_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ZainAli60/tuned_model

SGLang

How to use ZainAli60/tuned_model 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 "ZainAli60/tuned_model" \
    --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": "ZainAli60/tuned_model",
		"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 "ZainAli60/tuned_model" \
        --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": "ZainAli60/tuned_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ZainAli60/tuned_model with Docker Model Runner:
```
docker model run hf.co/ZainAli60/tuned_model
```

ZainAli60 commited on Feb 13, 2024

Commit

b2db15e

verified ·

1 Parent(s): 7d4a298

Upload FalconForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/pretraining/local-models/training/2024-02-13_11-06-27",
   "alibi": true,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [

 {
+  "_name_or_path": "/root/pretraining/local-models/training/2024-02-13_11-16-47",
   "alibi": true,
   "apply_residual_connection_post_layernorm": false,
   "architectures": [

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e1b88dc136770e38c844a3d1f21045a4dfdbd231198ede5260db2b90bdf9136
 size 5246534968

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d97e0f5bab8e1c39b0d06a620258b2c06162bc3379f98a062d5fbac3d019219
 size 5246534968