Downloads · 30 days
68
5% of all-time downloads
RichardErkhov/lgaalves_-_gpt2-xl_lima-gguf
lgaalves_-_gpt2-xl_lima-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
68
5% of all-time downloads
All-time downloads
1.4K
Public
Repo size
21.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf25.1 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gpt2-xl_lima - GGUF
| Name | Quant method | Size |
|---|---|---|
| gpt2-xl_lima.Q2_K.gguf | Q2_K | 0.84GB |
| gpt2-xl_lima.IQ3_XS.gguf | IQ3_XS | 0.84GB |
| gpt2-xl_lima.IQ3_S.gguf | IQ3_S | 0.84GB |
| gpt2-xl_lima.Q3_K_S.gguf | Q3_K_S | 0.84GB |
| gpt2-xl_lima.IQ3_M.gguf | IQ3_M | 0.91GB |
| gpt2-xl_lima.Q3_K.gguf | Q3_K | 0.97GB |
| gpt2-xl_lima.Q3_K_M.gguf | Q3_K_M | 0.97GB |
| gpt2-xl_lima.Q3_K_L.gguf | Q3_K_L | 1.03GB |
| gpt2-xl_lima.IQ4_XS.gguf | IQ4_XS | 0.9GB |
| gpt2-xl_lima.Q4_0.gguf | Q4_0 | 0.91GB |
| gpt2-xl_lima.IQ4_NL.gguf | IQ4_NL | 0.91GB |
| gpt2-xl_lima.Q4_K_S.gguf | Q4_K_S | 1.04GB |
| gpt2-xl_lima.Q4_K.gguf | Q4_K | 1.11GB |
| gpt2-xl_lima.Q4_K_M.gguf | Q4_K_M | 1.11GB |
| gpt2-xl_lima.Q4_1.gguf | Q4_1 | 1.0GB |
| gpt2-xl_lima.Q5_0.gguf | Q5_0 | 1.09GB |
| gpt2-xl_lima.Q5_K_S.gguf | Q5_K_S | 1.15GB |
| gpt2-xl_lima.Q5_K.gguf | Q5_K | 1.29GB |
| gpt2-xl_lima.Q5_K_M.gguf | Q5_K_M | 1.29GB |
| gpt2-xl_lima.Q5_1.gguf | Q5_1 | 1.18GB |
| gpt2-xl_lima.Q6_K.gguf | Q6_K | 1.52GB |
| gpt2-xl_lima.Q8_0.gguf | Q8_0 | 1.63GB |
license: mit datasets:
lgaalves/lgaalves/gpt2-xl_lima is an instruction fine-tuned model based on the GPT-2 transformer architecture.
| Metric | gpt2-xl_lima | gpt2-xl (base) |
|---|---|---|
| Avg. | 36.65 | 36.66 |
| ARC (25-shot) | 31.14 | 30.29 |
| HellaSwag (10-shot) | 51.28 | 51.38 |
| MMLU (5-shot) | 25.43 | 26.43 |
| TruthfulQA (0-shot) | 38.74 | 38.54 |
We use state-of-the-art Language Model Evaluation Harness to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard. Please see below for detailed instructions on reproducing benchmark results.
# Use a pipeline as a high-level helper
>>> from transformers import pipeline
>>> pipe = pipeline("text-generation", model="lgaalves/gpt2-xl_lima")
>>> question = "What is a large language model?"
>>> answer = pipe(question)
>>> print(answer[0]['generated_text'])
or, you can load the model direclty using:
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("lgaalves/gpt2-xl_lima")
model = AutoModelForCausalLM.from_pretrained("lgaalves/gpt2-xl_lima")
lgaalves/gpt2-xl_lima trained on the GAIR/lima.
lgaalves/gpt2-xl_lima was instruction fine-tuned using LoRA on 1 Tesla V100-SXM2-16GB. It took about 10 minutes to train it.
You can use the raw model for text generation or fine-tune it to a downstream task. The model was not extensively tested and may produce false information. It contains a lot of unfiltered content from the internet, which is far from neutral.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 29.95 |
| ARC (25-shot) | 31.14 |
| HellaSwag (10-shot) | 51.28 |
| MMLU (5-shot) | 25.43 |
| TruthfulQA (0-shot) | 38.74 |
| Winogrande (5-shot) | 57.22 |
| GSM8K (5-shot) | 0.91 |
| DROP (3-shot) | 4.89 |