Firworks
/

Llama-3.1-8B-Instruct-nvfp4

8-bit precision

compressed-tensors

Model card Files Files and versions

Firworks commited on Oct 25

Commit

7d92d1f

·

verified ·

1 Parent(s): 3c3cd91

Update README.md

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -11,4 +11,8 @@ base_model:
 **Base model:** `meta-llama/Llama-3.1-8B-Instruct`
 **How it was made:** One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration.
-> Notes: Keep `lm_head` in high precision; calibrate on long, domain-relevant sequences.

 **Base model:** `meta-llama/Llama-3.1-8B-Instruct`
 **How it was made:** One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration.
+> Notes: Keep `lm_head` in high precision; calibrate on long, domain-relevant sequences.
+Check the original model card for information about this model.
+If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to spread the adoption.