metadata
language:
- en
license: other
library_name: transformers
tags:
- axolotl
- finetune
- facebook
- meta
- pytorch
- llama
- llama-3
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.9
model_name: Llama-3-8B-Instruct-v0.10
pipeline_tag: text-generation
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
model-index:
- name: Llama-3-8B-Instruct-v0.10
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: 76.67
name: strict accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
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: 27.92
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
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: 4.91
name: exact match
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
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: 7.83
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
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: 10.81
name: acc_norm
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
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: 31.8
name: accuracy
source:
url: >-
https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/Llama-3-8B-Instruct-v0.10
name: Open LLM Leaderboard
![Llama-3 DPO Logo](/MaziyarPanahi/Llama-3-8B-Instruct-v0.10/resolve/main/llama-3-merges.webp)
Llama-3-8B-Instruct-v0.10
This model was developed based on MaziyarPanahi/Llama-3-8B-Instruct-v0.9
model.
β‘ Quantized GGUF
All GGUF models are available here: MaziyarPanahi/Llama-3-8B-Instruct-v0.10-GGUF
π 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):])