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

Libraries

How to use NoOrdinaryJoy/lora_model with Transformers:

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

pipe = pipeline("text-generation", model="NoOrdinaryJoy/lora_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NoOrdinaryJoy/lora_model")
model = AutoModelForCausalLM.from_pretrained("NoOrdinaryJoy/lora_model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NoOrdinaryJoy/lora_model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NoOrdinaryJoy/lora_model

SGLang

How to use NoOrdinaryJoy/lora_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 "NoOrdinaryJoy/lora_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": "NoOrdinaryJoy/lora_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 "NoOrdinaryJoy/lora_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": "NoOrdinaryJoy/lora_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use NoOrdinaryJoy/lora_model with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for NoOrdinaryJoy/lora_model to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for NoOrdinaryJoy/lora_model to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NoOrdinaryJoy/lora_model to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="NoOrdinaryJoy/lora_model",
    max_seq_length=2048,
)

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

NoOrdinaryJoy commited on Jun 15, 2024

Commit

facdc66

verified ·

1 Parent(s): 077cbab

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show

README.md +1 -1
adapter_config.json +3 -3
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,5 +1,4 @@
 ---
-base_model: unsloth/llama-3-8b-bnb-4bit
 language:
 - en
 license: apache-2.0
@@ -9,6 +8,7 @@ tags:
 - unsloth
 - llama
 - trl
 ---
 # Uploaded  model

 ---
 language:
 - en
 license: apache-2.0
 - unsloth
 - llama
 - trl
+base_model: unsloth/llama-3-8b-bnb-4bit
 ---
 # Uploaded  model

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,11 +21,11 @@
   "revision": "unsloth",
   "target_modules": [
     "o_proj",
-    "k_proj",
     "up_proj",
     "down_proj",
     "v_proj",
-    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "revision": "unsloth",
   "target_modules": [
     "o_proj",
+    "gate_proj",
     "up_proj",
     "down_proj",
     "v_proj",
+    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982a339fdece4bfb72d9af6f00e51a23c5bb4cc68320cc42ae9525ff710db670
 size 167832240

 version https://git-lfs.github.com/spec/v1
+oid sha256:7f8c6aa8874d7a17c294587f00a134d3a1f41c36f65fc7e4d32c2e74933000c6
 size 167832240