---

base_model: "meta-llama/Meta-Llama-3-8B-Instruct"
library_name: transformers
tags:
  - mergekit
  - merge
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
language:
  - en
pipeline_tag: text-generation
license: other
license_name: llama3
license_link: LICENSE
inference: false
model_creator: MaziyarPanahi
model_name: Llama-3-13B-Instruct-v0.1
quantized_by: MaziyarPanahi

---

![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)

# QuantFactory/Llama-3-13B-Instruct-v0.1-GGUF
This is quantized version of [MaziyarPanahi/Llama-3-13B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1) created using llama.cpp

# Original Model Card


<img src="./llama-3-merges.webp" alt="Goku 8x22B v0.1 Logo" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

# Llama-3-13B-Instruct-v0.1

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.

```python
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

```text
<|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!
```