Downloads · 30 days
11
9% of all-time downloads
hybridaione/perls-ministral-3-3b-sft
perls-ministral-3-3b-sft is a text generation model from hybridaione. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Full merged checkpoint of mistralai/Ministral-3-3B-Instruct-2512 fine-tuned (LoRA, merged) on Gestalt dialogue (Bry=user, Fritz=assistant) using 1–10 turn sliding windows from perls/perlssft.jsonl (combined perls.txt…
Downloads · 30 days
11
9% of all-time downloads
All-time downloads
117
Public
Parameters
3.8B
7.7 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors7.7 GB · 100%
From the Hugging Face model README
Full merged checkpoint of mistralai/Ministral-3-3B-Instruct-2512 fine-tuned (LoRA, merged) on Gestalt dialogue
(Bry=user, Fritz=assistant) using 1–10 turn sliding windows from perls/perls_sft.jsonl
(combined perls.txt + perls_synth.txt).
mistralai/Ministral-3-3B-Instruct-2512merge_and_unload)perls/perls_sft.jsonlmessages with user/assistant rolesperls/train_perls_sft_lora.pyRecommended sampling (matches training demo):
Example outputs after fine-tuning (using the same sampling parameters):
Ich bin gestresst. → [1, 15968, 12439, 8765, 1770, 1314, 1046]Ich kann mich nicht motivieren. → [1, 15968, 10248, 14557, 4041, 20746, 10412, 1046]Ich habe Angst. → [1, 15968, 16881, 62691, 1046]Wer sind Sie? → [1, 93896, 5989, 6441, 1063]Dr. Perls, was machen Sie? → [1, 16236, 1046, 4473, 11919, 1044, 1486, 31870, 6441, 1063]Was ist Gestalttherapie? → [1, 29269, 3444, 90905, 1781, 80159, 1063]import torch
from transformers import MistralCommonBackend, Mistral3ForConditionalGeneration
repo = "hybridaione/perls-ministral-3-3b-sft"
tok = MistralCommonBackend.from_pretrained(repo)
model = Mistral3ForConditionalGeneration.from_pretrained(
repo,
torch_dtype=torch.bfloat16,
device_map="auto"
).eval()
prompt = "Ich bin gestresst."
# Use tokenize=True for MistralCommonBackend
input_ids = tok.apply_chat_template(
[{"role": "user", "content": prompt}],
tokenize=True,
add_generation_prompt=True,
)
if hasattr(input_ids, 'input_ids'):
input_ids = input_ids.input_ids
inputs = {"input_ids": torch.tensor([input_ids]).to(model.device)}
out = model.generate(
**inputs,
max_new_tokens=256,
do_sample=True,
temperature=0.3,
min_p=0.15,
repetition_penalty=1.05,
pad_token_id=tok.pad_token_id,
)
print(tok.decode(out[0, inputs['input_ids'].shape[1]:], skip_special_tokens=True))
vLLM can load this merged checkpoint directly:
vllm serve hybridaione/perls-ministral-3-3b-sft \
--tensor-parallel-size 1 \
--max-model-len 2048