Instructions to use unsloth/llama-3-8b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/llama-3-8b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/llama-3-8b-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/llama-3-8b-Instruct")
model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/llama-3-8b-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/llama-3-8b-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/llama-3-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/llama-3-8b-Instruct

SGLang

How to use unsloth/llama-3-8b-Instruct 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 "unsloth/llama-3-8b-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/llama-3-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "unsloth/llama-3-8b-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/llama-3-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use unsloth/llama-3-8b-Instruct 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 unsloth/llama-3-8b-Instruct 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 unsloth/llama-3-8b-Instruct to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/llama-3-8b-Instruct to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/llama-3-8b-Instruct",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/llama-3-8b-Instruct with Docker Model Runner:
```
docker model run hf.co/unsloth/llama-3-8b-Instruct
```

danielhanchen commited on Apr 19, 2024

Commit

aa94a9c

verified ·

1 Parent(s): e9af1ab

Upload tokenizer

Browse files

Files changed (3) hide show

README.md +0 -1
special_tokens_map.json +2 -1
tokenizer_config.json +3 -2

README.md CHANGED Viewed

@@ -8,7 +8,6 @@ tags:
 - transformers
 - llama
 - llama-3
 ---
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

 - transformers
 - llama
 - llama-3
 ---
 # Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!

special_tokens_map.json CHANGED Viewed

@@ -12,5 +12,6 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
 }

     "normalized": false,
     "rstrip": false,
     "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
 }

tokenizer_config.json CHANGED Viewed

@@ -2050,7 +2050,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [
@@ -2058,6 +2058,7 @@
     "attention_mask"
   ],
   "model_max_length": 8192,
-  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

     }
   },
   "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [
     "attention_mask"
   ],
   "model_max_length": 8192,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }