Downloads · 30 days
49
3% of all-time downloads
RichardErkhov/frankenmerger_-_delta-4b-orange-gguf
frankenmerger_-_delta-4b-orange-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
49
3% of all-time downloads
All-time downloads
1.5K
Public
Repo size
53.7 GB
Likes
0
Public
Click a slice to open those files.
.gguf62.3 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
delta-4b-orange - GGUF
| Name | Quant method | Size |
|---|---|---|
| delta-4b-orange.Q2_K.gguf | Q2_K | 1.7GB |
| delta-4b-orange.IQ3_XS.gguf | IQ3_XS | 1.84GB |
| delta-4b-orange.IQ3_S.gguf | IQ3_S | 1.92GB |
| delta-4b-orange.Q3_K_S.gguf | Q3_K_S | 1.92GB |
| delta-4b-orange.IQ3_M.gguf | IQ3_M | 2.04GB |
| delta-4b-orange.Q3_K.gguf | Q3_K | 2.21GB |
| delta-4b-orange.Q3_K_M.gguf | Q3_K_M | 2.21GB |
| delta-4b-orange.Q3_K_L.gguf | Q3_K_L | 2.45GB |
| delta-4b-orange.IQ4_XS.gguf | IQ4_XS | 2.38GB |
| delta-4b-orange.Q4_0.gguf | Q4_0 | 2.48GB |
| delta-4b-orange.IQ4_NL.gguf | IQ4_NL | 2.51GB |
| delta-4b-orange.Q4_K_S.gguf | Q4_K_S | 2.51GB |
| delta-4b-orange.Q4_K.gguf | Q4_K | 2.7GB |
| delta-4b-orange.Q4_K_M.gguf | Q4_K_M | 2.7GB |
| delta-4b-orange.Q4_1.gguf | Q4_1 | 2.75GB |
| delta-4b-orange.Q5_0.gguf | Q5_0 | 3.01GB |
| delta-4b-orange.Q5_K_S.gguf | Q5_K_S | 3.01GB |
| delta-4b-orange.Q5_K.gguf | Q5_K | 3.13GB |
| delta-4b-orange.Q5_K_M.gguf | Q5_K_M | 3.13GB |
| delta-4b-orange.Q5_1.gguf | Q5_1 | 3.28GB |
| delta-4b-orange.Q6_K.gguf | Q6_K | 3.57GB |
| delta-4b-orange.Q8_0.gguf | Q8_0 | 4.63GB |
widget:
delta-4b-orange is frankenmerge of phi-2-orange-v2. The purpose is to create 4B parameters model based on Phi-2.
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "gmonsoon/delta-4b-orange"
messages = [{"role": "user", "content": "What is a large language model?"}]
tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])