BEE-spoke-data/Mixtral-GQA-400m-v2-GGUF

Quantized GGUF model files for Mixtral-GQA-400m-v2 from BEE-spoke-data

Name	Quant method	Size
mixtral-gqa-400m-v2.fp16.gguf	fp16	4.01 GB
mixtral-gqa-400m-v2.q2_k.gguf	q2_k	703.28 MB
mixtral-gqa-400m-v2.q3_k_m.gguf	q3_k_m	899.86 MB
mixtral-gqa-400m-v2.q4_k_m.gguf	q4_k_m	1.15 GB
mixtral-gqa-400m-v2.q5_k_m.gguf	q5_k_m	1.39 GB
mixtral-gqa-400m-v2.q6_k.gguf	q6_k	1.65 GB
mixtral-gqa-400m-v2.q8_0.gguf	q8_0	2.13 GB

Original Model Card:

BEE-spoke-data/Mixtral-GQA-400m-v2

testing code

# !pip install -U -q transformers datasets accelerate sentencepiece
import pprint as pp
from transformers import pipeline

pipe = pipeline(
    "text-generation",
    model="BEE-spoke-data/Mixtral-GQA-400m-v2",
    device_map="auto",
)
pipe.model.config.pad_token_id = pipe.model.config.eos_token_id

prompt = "My favorite movie is Godfather because"

res = pipe(
    prompt,
    max_new_tokens=256,
    top_k=4,
    penalty_alpha=0.6,
    use_cache=True,
    no_repeat_ngram_size=4,
    repetition_penalty=1.1,
    renormalize_logits=True,
)
pp.pprint(res[0])