Upload folder using huggingface_hub
Browse files- model.safetensors +1 -1
- recipe.yaml +0 -4
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 868745640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72ebf9b26b0422fdc8dd9900509f19a713490f5ae9a30fd28b182b94d0ae90a
|
3 |
size 868745640
|
recipe.yaml
CHANGED
@@ -8,10 +8,6 @@ sparsity_stage:
|
|
8 |
run_type: &id001 !!python/object/apply:llmcompressor.recipe.stage.StageRunType [oneshot]
|
9 |
quantization_stage:
|
10 |
quantization_modifiers:
|
11 |
-
ConstantPruningModifier:
|
12 |
-
targets: ['re:.*q_proj.weight', 're:.*k_proj.weight', 're:.*v_proj.weight', 're:.*o_proj.weight',
|
13 |
-
're:.*gate_proj.weight', 're:.*up_proj.weight', 're:.*down_proj.weight']
|
14 |
-
start: 0
|
15 |
QuantizationModifier:
|
16 |
targets: [Linear]
|
17 |
ignore: [lm_head]
|
|
|
8 |
run_type: &id001 !!python/object/apply:llmcompressor.recipe.stage.StageRunType [oneshot]
|
9 |
quantization_stage:
|
10 |
quantization_modifiers:
|
|
|
|
|
|
|
|
|
11 |
QuantizationModifier:
|
12 |
targets: [Linear]
|
13 |
ignore: [lm_head]
|