This model is a self-merge of
meta-llama/Meta-Llama-3-8B-Instruct
model.
How to use
You can use this model by using
MaziyarPanahi/Llama-3-13B-Instruct-v0.1
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-3-13B-Instruct-v0.1"
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.float16,
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=256,
eos_token_id=terminators,
do_sample=True,
temperature=0.6,
top_p=0.95,
)
print(outputs[0]["generated_text"][len(prompt):])
Prompt template
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>
what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!<|eot_id|>
To evaluate this expression, we need to follow the order of operations (PEMDAS):
1. First, multiply 4 and 2: 4*2 = 8
2. Then, subtract 8 from 25: 25 - 8 = 17
3. Finally, add 3: 17 + 3 = 20
So, 25-4*2+3 = 20!
Runs of MaziyarPanahi Llama-3-13B-Instruct-v0.1 on huggingface.co
61
Total runs
-2
24-hour runs
-5
3-day runs
-53
7-day runs
-262
30-day runs
More Information About Llama-3-13B-Instruct-v0.1 huggingface.co Model
More Llama-3-13B-Instruct-v0.1 license Visit here:
Llama-3-13B-Instruct-v0.1 huggingface.co is an AI model on huggingface.co that provides Llama-3-13B-Instruct-v0.1's model effect (), which can be used instantly with this MaziyarPanahi Llama-3-13B-Instruct-v0.1 model. huggingface.co supports a free trial of the Llama-3-13B-Instruct-v0.1 model, and also provides paid use of the Llama-3-13B-Instruct-v0.1. Support call Llama-3-13B-Instruct-v0.1 model through api, including Node.js, Python, http.
Llama-3-13B-Instruct-v0.1 huggingface.co is an online trial and call api platform, which integrates Llama-3-13B-Instruct-v0.1's modeling effects, including api services, and provides a free online trial of Llama-3-13B-Instruct-v0.1, you can try Llama-3-13B-Instruct-v0.1 online for free by clicking the link below.
MaziyarPanahi Llama-3-13B-Instruct-v0.1 online free url in huggingface.co:
Llama-3-13B-Instruct-v0.1 is an open source model from GitHub that offers a free installation service, and any user can find Llama-3-13B-Instruct-v0.1 on GitHub to install. At the same time, huggingface.co provides the effect of Llama-3-13B-Instruct-v0.1 install, users can directly use Llama-3-13B-Instruct-v0.1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Llama-3-13B-Instruct-v0.1 install url in huggingface.co: