|
--- |
|
base_model: tog/TinyLlama-1.1B-alpaca-chat-v1.5 |
|
datasets: |
|
- tatsu-lab/alpaca |
|
inference: false |
|
language: |
|
- en |
|
license: apache-2.0 |
|
model_creator: tog |
|
model_name: TinyLlama-1.1B-alpaca-chat-v1.5 |
|
pipeline_tag: text-generation |
|
quantized_by: afrideva |
|
tags: |
|
- gguf |
|
- ggml |
|
- quantized |
|
- q2_k |
|
- q3_k_m |
|
- q4_k_m |
|
- q5_k_m |
|
- q6_k |
|
- q8_0 |
|
widget: |
|
- text: '###Instruction:\nWhat is a large language model? Be concise\n\n### Response:\n' |
|
--- |
|
# tog/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF |
|
|
|
Quantized GGUF model files for [TinyLlama-1.1B-alpaca-chat-v1.5](https://huggingface.co/tog/TinyLlama-1.1B-alpaca-chat-v1.5) from [tog](https://huggingface.co/tog) |
|
|
|
|
|
| Name | Quant method | Size | |
|
| ---- | ---- | ---- | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q2_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q2_k.gguf) | q2_k | 482.14 MB | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q3_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q3_k_m.gguf) | q3_k_m | 549.85 MB | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q4_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q4_k_m.gguf) | q4_k_m | 667.81 MB | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q5_k_m.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q5_k_m.gguf) | q5_k_m | 782.04 MB | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q6_k.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q6_k.gguf) | q6_k | 903.41 MB | |
|
| [tinyllama-1.1b-alpaca-chat-v1.5.q8_0.gguf](https://huggingface.co/afrideva/TinyLlama-1.1B-alpaca-chat-v1.5-GGUF/resolve/main/tinyllama-1.1b-alpaca-chat-v1.5.q8_0.gguf) | q8_0 | 1.17 GB | |
|
|
|
|
|
|
|
## Original Model Card: |
|
|
|
## This Model |
|
|
|
This is the chat model finetuned on top of [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T). The dataset used is [tatsu-lab/stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca). |
|
|
|
Below is an instruction that describes a task. Write a response that appropriately completes the request. |
|
``` |
|
### Instruction: |
|
{instruction} |
|
|
|
### Response: |
|
``` |
|
|
|
You can use it with the `transformers` library: |
|
|
|
```python |
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "tog/TinyLlama-1.1B-alpaca-chat-v1.5" |
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
|
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
torch_dtype=torch.float16, |
|
device_map="auto") |
|
|
|
sequences = pipeline( |
|
'###Instruction:\nWhat is a large language model? Be concise.\n\n### Response:\n', |
|
do_sample=True, |
|
top_k=10, |
|
num_return_sequences=1, |
|
eos_token_id=tokenizer.eos_token_id, |
|
max_length=200) |
|
|
|
for seq in sequences: |
|
print(f"{seq['generated_text']}") |
|
``` |
|
|
|
You should get something along those lines: |
|
|
|
``` |
|
Setting `pad_token_id` to `eos_token_id`:2 for open-end generation. |
|
Result: ###Instruction: |
|
What is a large language model? Be concise. |
|
|
|
### Response: |
|
A large language model is a type of natural language understanding model that can learn to accurately recognize and interpret text data by understanding the context of words. Languages used for text understanding are typically trained on a corpus of text data. |
|
``` |