Hugging Face's logo

GreenBitAI
/
DeepSeek-V4.1-Flash-4bit-paged

Image-Text-to-Text
MLX
Safetensors
deepseek_v41
gbx-lm
apple-silicon
mixture-of-experts
4-bit precision
expert-paging
fp8
Model card Files
xet
 Community
yanghaojin commited on
Commit
2e2fc8a
·
verified ·
1 Parent(s): 706ca3c

Add files using upload-large-folder tool

Browse files
Files changed (8) hide show
  1. engram-layer-1/ple-q4.rows +3 -0
  2. engram-layer-1/ple_index.json +17 -0
  3. engram-layer-14/ple-q4.rows +3 -0
  4. engram-layer-14/ple_index.json +17 -0
  5. experts.bin +3 -0
  6. model.safetensors +3 -0
  7. mtp/mtp.safetensors +3 -0
  8. tokenizer.json +0 -0
engram-layer-1/ple-q4.rows ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8419a6231b4c7d9bb9051598f31a6c9ff4714f096b7c57ca280aef3e4191fb14
3
+ size 55296888192
engram-layer-1/ple_index.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "layout": "interleaved_q4",
4
+ "data_file": "ple-q4.rows",
5
+ "row_width": 256,
6
+ "row_count": 384006168,
7
+ "row_stride": 144,
8
+ "quantization": {
9
+ "bits": 4,
10
+ "group_size": 64,
11
+ "mode": "affine"
12
+ },
13
+ "shard_row_starts": [
14
+ 0
15
+ ],
16
+ "source": ""
17
+ }
engram-layer-14/ple-q4.rows ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813ef03744d31e969ce9888de75748bbe850f96ca908909ff0900d400a3f7a59
3
+ size 55298402208
engram-layer-14/ple_index.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "layout": "interleaved_q4",
4
+ "data_file": "ple-q4.rows",
5
+ "row_width": 256,
6
+ "row_count": 384016682,
7
+ "row_stride": 144,
8
+ "quantization": {
9
+ "bits": 4,
10
+ "group_size": 64,
11
+ "mode": "affine"
12
+ },
13
+ "shard_row_starts": [
14
+ 0
15
+ ],
16
+ "source": ""
17
+ }
experts.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e55e466b17413e6e4639354e7f1c538ad6630293eb15b0c7b32c06a641a56c
3
+ size 305764761600
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea0a0403a34a84a6f14822f99aaf17bbce6b8ab707eb2d3b2a08503a23a2bb8
3
+ size 11255291621
mtp/mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c086f128757987d03df4a68bebb7073953081b3900961e02f4069b309762b53f
3
+ size 8424620135
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff