Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


astrollama - GGUF
- Model creator: https://huggingface.co/universeTBD/
- Original model: https://huggingface.co/universeTBD/astrollama/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [astrollama.Q2_K.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q2_K.gguf) | Q2_K | 2.36GB |
| [astrollama.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [astrollama.IQ3_S.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [astrollama.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [astrollama.IQ3_M.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [astrollama.Q3_K.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q3_K.gguf) | Q3_K | 3.07GB |
| [astrollama.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [astrollama.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [astrollama.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [astrollama.Q4_0.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q4_0.gguf) | Q4_0 | 3.56GB |
| [astrollama.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [astrollama.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [astrollama.Q4_K.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q4_K.gguf) | Q4_K | 3.8GB |
| [astrollama.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [astrollama.Q4_1.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q4_1.gguf) | Q4_1 | 3.95GB |
| [astrollama.Q5_0.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q5_0.gguf) | Q5_0 | 4.33GB |
| [astrollama.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [astrollama.Q5_K.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q5_K.gguf) | Q5_K | 4.45GB |
| [astrollama.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [astrollama.Q5_1.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q5_1.gguf) | Q5_1 | 4.72GB |
| [astrollama.Q6_K.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q6_K.gguf) | Q6_K | 5.15GB |
| [astrollama.Q8_0.gguf](https://huggingface.co/RichardErkhov/universeTBD_-_astrollama-gguf/blob/main/astrollama.Q8_0.gguf) | Q8_0 | 6.67GB |




Original model description:
---
license: mit
datasets:
- universeTBD/arxiv-astro-abstracts-all
language:
- en
metrics:
- perplexity
pipeline_tag: text-generation
tags:
- llama-2
- astronomy
- astrophysics
- arxiv
inference: false
---

<p><h1>AstroLLaMA</h1></p>

**Play with the model in our Hugging Face space!** https://huggingface.co/spaces/universeTBD/astrollama

<p align="center">
  <img src="https://huggingface.co/universeTBD/astrollama/resolve/main/images/astrollama-logo.png" alt="AstroLLaMA" width="500px"/>
</p>

## Loading the model

```python
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    pretrained_model_name_or_path="universeTBD/astrollama"
)
model = AutoModelForCausalLM.from_pretrained(
    pretrained_model_name_or_path="universeTBD/astrollama",
    device_map="auto",
)
```

## Generating text from a prompt

```python
import torch
from transformers import pipeline

generator = pipeline(
    task="text-generation",
    model=model,
    tokenizer=tokenizer,
    device_map="auto"
)

# Taken from https://arxiv.org/abs/2308.12823
prompt = "In this letter, we report the discovery of the highest redshift, " \
    "heavily obscured, radio-loud QSO candidate selected using JWST NIRCam/MIRI, " \
    "mid-IR, sub-mm, and radio imaging in the COSMOS-Web field. "

# For reproducibility
torch.manual_seed(42)

generated_text = generator(
    prompt,
    do_sample=True,
    max_length=512
)
```

## Embedding text with AstroLLaMA

```python
texts = [
    "Abstract 1",
    "Abstract 2"
]
inputs = tokenizer(
    texts,
    return_tensors="pt",
    return_token_type_ids=False,
    padding=True,
    truncation=True,
    max_length=4096
)
inputs.to(model.device)
outputs = model(**inputs, output_hidden_states=True)

# Last layer of the hidden states. Get average embedding of all tokens
embeddings = outputs["hidden_states"][-1][:, 1:, ...].mean(1).detach().cpu().numpy()
```