Neooooo commited on
Commit
5ac4fa9
·
verified ·
1 Parent(s): 691aabb

Upload quant-forge artifacts

Browse files
Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -1,3 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # Neooooo/qf-integration-test
2
 
3
  ## QuantForge Metadata
@@ -11,6 +24,9 @@
11
 
12
  ## Accuracy (BF16 vs NVFP4)
13
 
 
 
 
14
  | Task | Metric | BF16 | NVFP4 | Recovery |
15
  |---|---:|---:|---:|---:|
16
  | arc_challenge | acc,none | 0.5000 | n/a | n/a |
 
1
+ ---
2
+ base_model: Qwen/Qwen3-30B-A3B
3
+ datasets:
4
+ - HuggingFaceH4/ultrachat_200k
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
+ quantized_by: QuantForge
8
+ tags:
9
+ - quantforge
10
+ - quantized
11
+ - nvfp4
12
+ ---
13
+
14
  # Neooooo/qf-integration-test
15
 
16
  ## QuantForge Metadata
 
24
 
25
  ## Accuracy (BF16 vs NVFP4)
26
 
27
+ _Recovery status: partial_
28
+ _Details: Quantized evaluation unavailable due to current vLLM MoE quantization compatibility in this environment._
29
+
30
  | Task | Metric | BF16 | NVFP4 | Recovery |
31
  |---|---:|---:|---:|---:|
32
  | arc_challenge | acc,none | 0.5000 | n/a | n/a |