Downloads · 30 days
99
5% of all-time downloads
vuiseng9_-_ov-gpt2-fp32-no-cache-gguf
RichardErkhov/vuiseng9_-_ov-gpt2-fp32-no-cache-gguf
vuiseng9_-_ov-gpt2-fp32-no-cache-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.
All-time downloads
1.8K
Public
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.4 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 26, 2024
- Updated
- Aug 26, 2024
- SHA
- ad6f69f4
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
ov-gpt2-fp32-no-cache - GGUF
- Model creator: https://huggingface.co/vuiseng9/
- Original model: https://huggingface.co/vuiseng9/ov-gpt2-fp32-no-cache/
| Name | Quant method | Size |
|---|---|---|
| ov-gpt2-fp32-no-cache.Q2_K.gguf | Q2_K | 0.08GB |
| ov-gpt2-fp32-no-cache.IQ3_XS.gguf | IQ3_XS | 0.08GB |
| ov-gpt2-fp32-no-cache.IQ3_S.gguf | IQ3_S | 0.08GB |
| ov-gpt2-fp32-no-cache.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| ov-gpt2-fp32-no-cache.IQ3_M.gguf | IQ3_M | 0.09GB |
| ov-gpt2-fp32-no-cache.Q3_K.gguf | Q3_K | 0.09GB |
| ov-gpt2-fp32-no-cache.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| ov-gpt2-fp32-no-cache.Q3_K_L.gguf | Q3_K_L | 0.1GB |
| ov-gpt2-fp32-no-cache.IQ4_XS.gguf | IQ4_XS | 0.1GB |
| ov-gpt2-fp32-no-cache.Q4_0.gguf | Q4_0 | 0.1GB |
| ov-gpt2-fp32-no-cache.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| ov-gpt2-fp32-no-cache.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| ov-gpt2-fp32-no-cache.Q4_K.gguf | Q4_K | 0.11GB |
| ov-gpt2-fp32-no-cache.Q4_K_M.gguf | Q4_K_M | 0.11GB |
| ov-gpt2-fp32-no-cache.Q4_1.gguf | Q4_1 | 0.11GB |
| ov-gpt2-fp32-no-cache.Q5_0.gguf | Q5_0 | 0.11GB |
| ov-gpt2-fp32-no-cache.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| ov-gpt2-fp32-no-cache.Q5_K.gguf | Q5_K | 0.12GB |
| ov-gpt2-fp32-no-cache.Q5_K_M.gguf | Q5_K_M | 0.12GB |
| ov-gpt2-fp32-no-cache.Q5_1.gguf | Q5_1 | 0.12GB |
| ov-gpt2-fp32-no-cache.Q6_K.gguf | Q6_K | 0.13GB |
| ov-gpt2-fp32-no-cache.Q8_0.gguf | Q8_0 | 0.17GB |
Original model description:
Notes:
This model is inherited directly from gpt2 in HF model hub. Then, GPT2 Openvino IR from OMZ is copied here. The intended usage of this model is for optimum-intel.
# Install Optimum-Intel
from transformers import AutoTokenizer, pipeline, set_seed, AutoModelForCausalLM
from optimum.intel.openvino import OVModelForCausalLM
model_id="vuiseng9/ov-gpt2-fp32-no-cache"
model = OVModelForCausalLM.from_pretrained(model_id, use_cache=False)
tokenizer = AutoTokenizer.from_pretrained(model_id)
generator_pipe = pipeline('text-generation', model=model, tokenizer=tokenizer)
output = generator_pipe("It's a beautiful day ...", max_length=30, num_return_sequences=1)
- Created
- Aug 26, 2024
- Updated
- Aug 26, 2024