Instructions to use YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco with Transformers:

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

pipe = pipeline("text-generation", model="YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco")
model = AutoModelForCausalLM.from_pretrained("YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco

SGLang

How to use YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco 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 "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco" \
    --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": "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco",
		"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 "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco" \
        --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": "YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco with Docker Model Runner:
```
docker model run hf.co/YeonwooSung/llama-3.1-8B-Galore-openassistant-guanaco
```

llama-3.1-8B-Galore-openassistant-guanaco / README.md

Yeonwoo Sung

leaderboard-pr-bot

Adding Evaluation Results (#1)

76c8a1a verified almost 2 years ago

preview code

Raw History Blame Contribute Delete

3.61 kB

	---
	library_name: transformers
	tags:
	- trl
	- sft
	model-index:
	- name: llama-3.1-8B-Galore-openassistant-guanaco
	results:
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: IFEval (0-Shot)
	type: HuggingFaceH4/ifeval
	args:
	num_few_shot: 0
	metrics:
	- type: inst_level_strict_acc and prompt_level_strict_acc
	value: 26.35
	name: strict accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: BBH (3-Shot)
	type: BBH
	args:
	num_few_shot: 3
	metrics:
	- type: acc_norm
	value: 31.44
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MATH Lvl 5 (4-Shot)
	type: hendrycks/competition_math
	args:
	num_few_shot: 4
	metrics:
	- type: exact_match
	value: 4.83
	name: exact match
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: GPQA (0-shot)
	type: Idavidrein/gpqa
	args:
	num_few_shot: 0
	metrics:
	- type: acc_norm
	value: 6.71
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MuSR (0-shot)
	type: TAUR-Lab/MuSR
	args:
	num_few_shot: 0
	metrics:
	- type: acc_norm
	value: 14.58
	name: acc_norm
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	- task:
	type: text-generation
	name: Text Generation
	dataset:
	name: MMLU-PRO (5-shot)
	type: TIGER-Lab/MMLU-Pro
	config: main
	split: test
	args:
	num_few_shot: 5
	metrics:
	- type: acc
	value: 24.52
	name: accuracy
	source:
	url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=BlackBeenie/llama-3.1-8B-Galore-openassistant-guanaco
	name: Open LLM Leaderboard
	---

	# Model Card for Model ID

	## Model Details

	## Training Details

	### Training Data

	[timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)

	### Training Procedure

	Trained with SFTTrainer with Galore quantization.

	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BlackBeenie__llama-3.1-8B-Galore-openassistant-guanaco)

	\| Metric \|Value\|
	\|-------------------\|----:\|
	\|Avg. \|18.07\|
	\|IFEval (0-Shot) \|26.35\|
	\|BBH (3-Shot) \|31.44\|
	\|MATH Lvl 5 (4-Shot)\| 4.83\|
	\|GPQA (0-shot) \| 6.71\|
	\|MuSR (0-shot) \|14.58\|
	\|MMLU-PRO (5-shot) \|24.52\|