Hugging Face's logo

PrunaAI
/
Sungmanc-finetune_smollm2_python-HQQ-8bit-smashed

llama
pruna-ai
Model card Files
xet
Community
2

Upload folder using huggingface_hub

#2
by sharpenb - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+3
-3
Files changed (3) hide show
  1. config.json +1 -1
  2. qmodel.pt +1 -1
  3. smash_config.json +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/models/tmp4x_575cb/tmphvbs_znq",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/tmp/models/tmp3wqlu0d7/tmpm32zpjz2",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
qmodel.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9052a472f80c91783b474361bbc039ffa3e46bd8c9115c6f9995c834a7c34f9e
3
  size 2215167664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccd638a6a49678a44c78e5cb47be48953219cbf93108191d2a0275e5ede40ee
3
  size 2215167664
smash_config.json CHANGED
@@ -26,7 +26,7 @@
26
  "quant_hqq_weight_bits": 8,
27
  "max_batch_size": 1,
28
  "device": "cuda",
29
- "cache_dir": "/tmp/models/tmp4x_575cb",
30
  "task": "",
31
  "save_load_fn": "hqq",
32
  "save_load_fn_args": {},
 
26
  "quant_hqq_weight_bits": 8,
27
  "max_batch_size": 1,
28
  "device": "cuda",
29
+ "cache_dir": "/tmp/models/tmp3wqlu0d7",
30
  "task": "",
31
  "save_load_fn": "hqq",
32
  "save_load_fn_args": {},