language, license, library_name, tags, base_model, model_name, pipeline_tag, license_name, license_link, inference, model_creator, model-index

language	license	library_name	tags	base_model	model_name	pipeline_tag	license_name	license_link	inference	model_creator	model-index
en	other	transformers	axolotl finetune facebook meta pytorch llama llama-3	MaziyarPanahi/Llama-3-8B-Instruct-v0.9	Llama-3-8B-Instruct-v0.10	text-generation	llama3	LICENSE	false	MaziyarPanahi	name results Llama-3-8B-Instruct-v0.10 task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 76.67 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 27.92 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 4.91 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 7.83 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 10.81 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 31.8 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10 Open LLM Leaderboard

Llama-3-8B-Instruct-v0.10

This model was developed based on MaziyarPanahi/Llama-3-8B-Instruct-v0.9 model.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/Llama-3-8B-Instruct-v0.10-GGUF

🏆 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.66
IFEval (0-Shot)	76.67
BBH (3-Shot)	27.92
MATH Lvl 5 (4-Shot)	4.91
GPQA (0-shot)	7.83
MuSR (0-shot)	10.81
MMLU-PRO (5-shot)	31.80

Prompt Template

This model uses ChatML prompt template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

How to use

You can use this model by using MaziyarPanahi/Llama-3-8B-Instruct-v0.10 as the model name in Hugging Face's transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
from transformers import pipeline
import torch

model_id = "MaziyarPanahi/Llama-3-8B-Instruct-v0.10"

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
    # attn_implementation="flash_attention_2"
)

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True
)

streamer = TextStreamer(tokenizer)

pipeline = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    model_kwargs={"torch_dtype": torch.bfloat16},
    streamer=streamer
)

# Then you can use the pipeline to generate text.

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

terminators = [
    tokenizer.eos_token_id,    
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=512,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.105,
)
print(outputs[0]["generated_text"][len(prompt):])