Hugging Face's logo

relaxml
/
Llama-2-70b-E8P-2Bit

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
4

Upload folder using huggingface_hub

#3
by at676 - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+170
-566
Files changed (4) hide show
  1. config.json +5 -1
  2. model-00001-of-00002.safetensors +2 -2
  3. model-00002-of-00002.safetensors +2 -2
  4. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -18,10 +18,14 @@
18
  "pretraining_tp": 1,
19
  "quip_params": {
20
  "codebook": "E8P12",
 
21
  "codesz": 8,
22
- "idx_dtype": "torch.int16",
 
23
  "lora_rank": 0,
 
24
  "outlier_channel_split": false,
 
25
  "rescale_WH": false
26
  },
27
  "rms_norm_eps": 1e-05,
 
18
  "pretraining_tp": 1,
19
  "quip_params": {
20
  "codebook": "E8P12",
21
+ "codebook_version": 1,
22
  "codesz": 8,
23
+ "fused": true,
24
+ "idx_dtype": "torch.int64",
25
  "lora_rank": 0,
26
+ "model_version": 1,
27
  "outlier_channel_split": false,
28
+ "packsz": 4,
29
  "rescale_WH": false
30
  },
31
  "rms_norm_eps": 1e-05,
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d21fa61b8d2b8d4b8125ce958c6ab034185615ab8280aa3a451e07c18a47fee6
3
- size 9987779322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:389e389c2ddd4b2766730c214f4d56f283d8c3acc15dfccc8947511b1ccdf317
3
+ size 9987761802
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:105e334872c6446ac11129ebb89cf1e839c5939f7ec0c84f878552b148d766bb
3
- size 8198397262
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f0cb174525bc8aaa6bb90d109f3d9ace66a06d2d1c9c3c38f9d592791dec15
3
+ size 8198383918
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff