129 lines
3.1 KiB
Markdown
129 lines
3.1 KiB
Markdown
|
|
---
|
|
|
|
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
|
|
|
|
---
|
|
|
|
|
|
|
|
# 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!
|
|
```
|