Downloads · 30 days
2
5% of all-time downloads
Kerwin0113/GSW-Llama3.2-1B-20251207-0837-GGUF
GSW-Llama3.2-1B-20251207-0837-GGUF is a machine learning model from Kerwin0113. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- 微调模型: GSW-Llama3.2-1B-20251207-0837 - 基座模型: unsloth/Llama-3.2-1B-Instruct - 量化方法: q4km - Chat Template: llama-3.1 - 训练框架: Unsloth + TRL
Downloads · 30 days
2
5% of all-time downloads
All-time downloads
41
Public
Repo size
808 MB
Likes
0
Public
Click a slice to open those files.
.gguf808 MB · 100%
From the Hugging Face model README
llama-3.1# 创建模型
ollama create gsw-llama3.2-1b-20251207-0837 -f Modelfile
# 运行模型
ollama run gsw-llama3.2-1b-20251207-0837
# 使用 GPU 加速 (ngl=99 表示所有层都放到 GPU)
./llama-cli -m GSW-Llama3.2-1B-20251207-0837-Q4_K_M.gguf -p "你的问题" -ngl 99
# 交互模式
./llama-cli -m GSW-Llama3.2-1B-20251207-0837-Q4_K_M.gguf -i -ngl 99
llama-3.1llama-3.1temperature: 0.7
top_p: 0.9
repetition_penalty: 1.05
max_tokens: 4096