ysingh-aiml/tinyllama-alpaca-lora-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
tinyllama-alpaca-lora-gguf/README.md
ModelHub XC 521db14247 初始化项目，由ModelHub XC社区提供模型 
Model: ysingh-aiml/tinyllama-alpaca-lora-gguf
Source: Original Platform
2026-04-12 19:25:57 +08:00

1.2 KiB
Raw Permalink Blame History

license, language, base_model, tags, datasets
license language base_model tags datasets
apache-2.0
en
TinyLlama/TinyLlama-1.1B-Chat-v1.0
gguf
llama-cpp
quantized
tinyllama
lora
alpaca
text-generation
tatsu-lab/alpaca

TinyLlama 1.1B — LoRA (Alpaca) — GGUF quantizations

GGUF weights for TinyLlama-1.1B-Chat fine-tuned with LoRA on Alpaca-style instructions (fused HF checkpoint → F16 GGUF → llama-quantize).

Files

File Quantization ~Size
model-Q4_K_M.gguf Q4_K_M ~637 MB
model-Q5_K_M.gguf Q5_K_M ~746 MB
model-Q8_0.gguf Q8_0 ~1.1 GB

Usage (llama.cpp)

llama-cli -m model-Q4_K_M.gguf -p "Hello" -n 128
# or
llama-server -m model-Q4_K_M.gguf --host 0.0.0.0 --port 8080

Provenance

  • Base: TinyLlama/TinyLlama-1.1B-Chat-v1.0
  • Conversion: llama.cpp/convert_hf_to_gguf.py (F16), then llama-quantize
  • Chat template is embedded in the GGUF (TinyLlama chat format)

Related