koesn / llama3-8b-instruct

Fixed num_ctx to 8192 and eos token. This Llama 3 8B Instruct model is ready to use for full model's 8k contexts window.

396 6 months ago

5 Tags
latest
c40cd0e317f3 • 4.7GB • 6 months ago
Q4_0
c40cd0e317f3 • 4.7GB • 6 months ago
Q4_K_M
aae5b523ef30 • 4.9GB • 6 months ago
Q5_K_M
7f44284ae112 • 5.7GB • 6 months ago
Q6_K
a3288dbaf70c • 6.6GB • 6 months ago