Downloads · 30 days
147
6% of all-time downloads
DarkKitsune/LFM2.5-8B-A1B-Opus-Distil-Q5_K_M-imat-GGUF
LFM2.5-8B-A1B-Opus-Distil-Q5_K_M-imat-GGUF is a text generation model from DarkKitsune. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
Quantized to Q5KM with importance matrices for higher accuracy.
Downloads · 30 days
147
6% of all-time downloads
All-time downloads
2.4K
Public
Repo size
6.1 GB
Likes
3
Public
Click a slice to open those files.
.gguf6 GB · 100%
From the Hugging Face model README
Quantized to Q5_K_M with importance matrices for higher accuracy.
This model is a fine-tuned version of LiquidAI/LFM2.5-8B-A1B, adapted on the angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k dataset for English text-generation and reasoning-style responses.
The fine-tuning run used a custom Convergent Intelligence optimizer stack, CIxOpt, designed for heterogeneous routing across parameter types. The goal of this checkpoint is to test whether a Liquid Foundation Model backbone can be adapted efficiently through targeted sparse participation rather than broad full-model modification.
This is an experimental research checkpoint intended for continued evaluation, domain adaptation, and architecture/optimizer testing.
Fine-tuning data:
The dataset was processed into chat-style training examples using tokenizer-compatible chat formatting where available. Empty or malformed examples were filtered before tokenization.
This model was trained using the Convergent Intelligence CIxOpt optimizer framework.
CIxOpt applies heterogeneous routing based on parameter type and tensor structure:
The fine-tuning strategy was designed to avoid unnecessary modification of the full pretrained backbone. Instead, training focused on selected adaptation surfaces, especially upper-layer projection and normalization modules.
The intended training philosophy was:
text freeze most pretrained structure adapt upper reasoning / response-shaping layers preserve lower representational substrate route parameter groups by optimizer behavior
This makes the checkpoint useful for studying efficient adaptation of LFM-family models under constrained compute.
This model is intended for:
Example use cases:
This model is not intended for high-stakes autonomous deployment without additional evaluation.
Do not use this model as the sole decision-maker for:
This is an experimental fine-tuned checkpoint. Known or expected limitations include:
Users should independently validate important outputs. Generated content may be plausible but incorrect.
For deployment-facing use, additional steps are recommended:
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "reaperdoesntknow/LFM2.5-8B-A1B-Opus-Distil"
tokenizer = AutoTokenizer.from_pretrained(
model_id,
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True,
)
if tokenizer.pad_token is None:
tokenizer.pad_token = tokenizer.eos_token
prompt = "Explain why stable positional encoding matters for long-context language models."
inputs = tokenizer(
prompt,
return_tensors="pt",
).to(model.device)
with torch.inference_mode():
output = model.generate(
**inputs,
max_new_tokens=1024,
do_sample=True,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.05,
pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Approximate training configuration used:
text base_model: LiquidAI/LFM2.5-8B-A1B dataset: angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k task: causal language modeling / instruction-style SFT optimizer: CIxOpt state_dtype: fp32 weight_decay: enabled gradient_clipping: enabled chat_template: tokenizer-compatible formatting padding: max_length loss_masking: padding tokens masked with -100
Exact loss curves, benchmark scores, and hardware details should be added after evaluation.
Formal benchmark results have not yet been added.
Recommended evaluation targets:
Base model:
bibtex @misc{liquidai_lfm25, title = {LFM2.5-8B-A1B}, author = {Liquid AI}, year = {2025}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/LiquidAI/LFM2.5-8B-A1B}} }
Fine-tuning dataset:
bibtex @misc{angrygiraffe_reasoning_dataset, title = {claude-opus-4.6-4.7-reasoning-8.7k}, author = {angrygiraffe}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/datasets/angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k}} }
Fine-tuning and optimizer experimentation by: Convergent Intelligence LLC | Research & Development Divisions Research and development focus: AI systems, intelligence analysis, mathematical frameworks, optimizer design, and efficient model adaptation.
This model is provided for research and experimentation. It should not be treated as a verified expert system. Outputs require human review, especially in factual, technical, legal, medical, financial, operational, or safety-critical contexts.
<!-- cix-keeper-ts:2026-07-02T13:15:52Z -->