Hugging Face's logo

litert-community
/
Hy-MT2-1.8B

Translation
LiteRT-LM
LiteRT
litertlm
on-device
edge
hunyuan
multilingual
Model card Files
xet
 Community
mlboydaisuke commited on
Commit
18cc1a6
·
verified ·
1 Parent(s): 617f1ef

Chat template: accept the 0.18 content-parts form (string form unchanged); weights, tokenizer and executor metadata byte-identical

Browse files
Files changed (3) hide show
  1. Hy-MT2-1.8B_int8.litertlm +1 -1
  2. README.md +2 -0
  3. litertlm_manifest.json +3 -3
Hy-MT2-1.8B_int8.litertlm CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bbd0b65d7e69c8d92b8ab3033e353536ef40c77f4dc5f4c32f2931417c13eda
3
  size 1815622960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529e6d378df5869d89a5a08717c06604105a32d8a4dab4800175d6baabc4da50
3
  size 1815622960
README.md CHANGED
@@ -64,6 +64,8 @@ Hy-MT2-1.8B is Tencent's "fast-thinking" multilingual **translation model**: 33
64
  |---|---|---|
65
  | `Hy-MT2-1.8B_int8.litertlm` | export-time dynamic int8 (linears + embedding) | 1.82 GB |
66
 
 
 
67
  ## Correctness
68
 
69
  All numbers below were measured on **this exact file** (litert-lm 0.16.0, Apple M4 Max).
 
64
  |---|---|---|
65
  | `Hy-MT2-1.8B_int8.litertlm` | export-time dynamic int8 (linears + embedding) | 1.82 GB |
66
 
67
+ 2026-09-21: chat template updated to accept the 0.18 content-parts form (string form unchanged); weights, tokenizer and executor metadata byte-identical.
68
+
69
  ## Correctness
70
 
71
  All numbers below were measured on **this exact file** (litert-lm 0.16.0, Apple M4 Max).
litertlm_manifest.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "manifest_schema": "0.1.2",
3
  "repo": "litert-community/Hy-MT2-1.8B",
4
- "generated": "2026-09-06",
5
  "generator": "make_manifest.py",
6
  "model": {
7
  "display_name": "Hy-MT2-1.8B",
@@ -21,12 +21,12 @@
21
  "variants": [
22
  {
23
  "file": "Hy-MT2-1.8B_int8.litertlm",
24
- "sha256": "7bbd0b65d7e69c8d92b8ab3033e353536ef40c77f4dc5f4c32f2931417c13eda",
25
  "size_bytes": 1815622960,
26
  "sections": [
27
  {
28
  "type": "LlmMetadataProto",
29
- "size_bytes": 673
30
  },
31
  {
32
  "type": "HF_Tokenizer_Zlib",
 
1
  {
2
  "manifest_schema": "0.1.2",
3
  "repo": "litert-community/Hy-MT2-1.8B",
4
+ "generated": "2026-09-22",
5
  "generator": "make_manifest.py",
6
  "model": {
7
  "display_name": "Hy-MT2-1.8B",
 
21
  "variants": [
22
  {
23
  "file": "Hy-MT2-1.8B_int8.litertlm",
24
+ "sha256": "529e6d378df5869d89a5a08717c06604105a32d8a4dab4800175d6baabc4da50",
25
  "size_bytes": 1815622960,
26
  "sections": [
27
  {
28
  "type": "LlmMetadataProto",
29
+ "size_bytes": 1056
30
  },
31
  {
32
  "type": "HF_Tokenizer_Zlib",