You can deploy this model and start earning money today!

RichardErkhov/
AI-Sweden-Models_-_Llama-3-8B-instruct-gguf

Name: AI-Sweden-Models_-_Llama-3-8B-instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-8B-instruct - GGUF

Model creator: https://huggingface.co/AI-Sweden-Models/
Original model: https://huggingface.co/AI-Sweden-Models/Llama-3-8B-instruct/

Name	Quant method	Size
Llama-3-8B-instruct.Q2_K.gguf	Q2_K	2.96GB
Llama-3-8B-instruct.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3-8B-instruct.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3-8B-instruct.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3-8B-instruct.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3-8B-instruct.Q3_K.gguf	Q3_K	3.74GB
Llama-3-8B-instruct.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3-8B-instruct.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3-8B-instruct.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3-8B-instruct.Q4_0.gguf	Q4_0	4.34GB
Llama-3-8B-instruct.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3-8B-instruct.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3-8B-instruct.Q4_K.gguf	Q4_K	4.58GB
Llama-3-8B-instruct.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3-8B-instruct.Q4_1.gguf	Q4_1	4.78GB
Llama-3-8B-instruct.Q5_0.gguf	Q5_0	5.21GB
Llama-3-8B-instruct.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3-8B-instruct.Q5_K.gguf	Q5_K	5.34GB
Llama-3-8B-instruct.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3-8B-instruct.Q5_1.gguf	Q5_1	5.65GB
Llama-3-8B-instruct.Q6_K.gguf	Q6_K	6.14GB
Llama-3-8B-instruct.Q8_0.gguf	Q8_0	7.95GB

Original model description:

language:

sv
da
'no' license: llama3 base_model: AI-Sweden-Models/Llama-3-8B

Checkpoint 1

Training setup

The training was perfomed on the LUMI supercomputer within the DeployAI EU project. Based of the base model AI-Sweden-Models/Llama-3-8B.

Dataset

A data recipe by: 42 Labs

How to use

python

import transformers
import torch

model_id = "AI-Sweden-Models/Llama-3-8B-instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "Du är en hjälpsam assistant som svarar klokt och vänligt."},
    {"role": "user", "content": "Hur gör man pannkakor? Och vad behöver man handla? Undrar också vad 5+6 är.."},
]

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][-1])