Downloads · 30 days
4
9% of all-time downloads
RichardErkhov/timpal0l_-_Mistral-7B-v0.1-flashback-v2-instruct-4bits
timpal0l_-_Mistral-7B-v0.1-flashback-v2-instruct-4bits 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
4
9% of all-time downloads
All-time downloads
46
Public
Parameters
7.4B
4.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.5 GB · 100%
How the weights are stored.
U87B · 95%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Mistral-7B-v0.1-flashback-v2-instruct - bnb 4bits
language:
Mistral-7B-v0.1-flashback-v2-instruct is an instruct based version of the base model timpal0l/Mistral-7B-v0.1-flashback-v2. It has been finetuned on a the machine translated instruct dataset OpenHermes2.5.
from transformers import pipeline
pipe = pipeline(
"text-generation",
"timpal0l/Mistral-7B-v0.1-flashback-v2-instruct",
device_map="auto"
)
text = """
Hur många ägg har jag? Jag hade 10 ägg, sen gav jag bort 5 ägg.
Sen fick jag 3 ägg av en kompis.
"""
generated = pipe(f"USER:{text}ASSISTANT:", max_length=512, temperature=0.6)
print(generated[0]["generated_text"].split("ASSISTANT: ")[1:][0])
Output:
Du har 8 ägg. Här är resonemanget:
1. Du börjar med 10 ägg
2. Du ger bort 5 ägg, vilket lämnar dig med 10 - 5 = 5 ägg
3. Sedan får du 3 ägg av en kompis, vilket gör att du har 5 + 3 = 8 ägg.