Hugging Face's logo

llm-jp
/
llm-jp-3-8x1.8b-instruct3

Text Generation
Transformers
Safetensors
English
Japanese
mixtral
conversational
text-generation-inference
Model card Files Community
Taka008 commited on
Commit
6121a27
·
2 Parent(s): e53de85 30250b5

merge bf16

Browse files
Files changed (10) hide show
  1. config.json +2 -2
  2. model-00001-of-00008.safetensors → model-00001-of-00004.safetensors +2 -2
  3. model-00002-of-00008.safetensors → model-00002-of-00004.safetensors +2 -2
  4. model-00003-of-00008.safetensors → model-00003-of-00004.safetensors +2 -2
  5. model-00004-of-00008.safetensors → model-00004-of-00004.safetensors +2 -2
  6. model-00005-of-00008.safetensors +0 -3
  7. model-00006-of-00008.safetensors +0 -3
  8. model-00007-of-00008.safetensors +0 -3
  9. model-00008-of-00008.safetensors +0 -3
  10. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "llm-jp/llm-jp-3-8x1.8b-instruct3",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
@@ -27,7 +27,7 @@
27
  "router_jitter_noise": 0.0,
28
  "sliding_window": null,
29
  "tie_word_embeddings": false,
30
- "torch_dtype": "float32",
31
  "transformers_version": "4.47.0",
32
  "use_cache": true,
33
  "vocab_size": 99584
 
1
  {
2
+ "_name_or_path": "/home/shared/experiments/0117_moe-tuning/checkpoints/nemo-to-hf/dpo-RvNMnZvUJs",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
 
27
  "router_jitter_noise": 0.0,
28
  "sliding_window": null,
29
  "tie_word_embeddings": false,
30
+ "torch_dtype": "bfloat16",
31
  "transformers_version": "4.47.0",
32
  "use_cache": true,
33
  "vocab_size": 99584
model-00001-of-00008.safetensors → model-00001-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d011d00b72acd5dc2ac45ae543cd8d84d622fdf5f9ef009bb9d6668c141acd33
3
- size 4951616224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf07f80dc6da3b0429735848ba5d3febd4e4460e9132789246881451a5ad339d
3
+ size 4988379392
model-00002-of-00008.safetensors → model-00002-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:174b39993d5f084379222a4f1f331a0906c4125eacc27d2d4e1f57a80190800d
3
- size 4966397176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3dfa13b26ff572e763469382a09d89f3c289ac3095c18b8c78f701b2127d68
3
+ size 4987299352
model-00003-of-00008.safetensors → model-00003-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5acda2b4251f6f886da5276188ca8a84e70cdbfc6bc4fca6f7678caa850cdadd
3
- size 4957925968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce302c905d88c2a7896468a88c22065f3011b436f9cd26469434b15f712fe0bf
3
+ size 4991535416
model-00004-of-00008.safetensors → model-00004-of-00004.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:843bb4888da7ebb9b91ea3e058ed531057b94a8cfa84414034d5cdfa404d6890
3
- size 4957926056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9267aa0bbb093323186b1d2ae0eebb7805ce7e93624d28c0b8a5db93d3e4e35e
3
+ size 3566400304
model-00005-of-00008.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4804dd16b18abb8280cc7f314cf9d569f4b40c265f00d45b09faa02b9be001fc
3
- size 4966397280
 
 
 
 
model-00006-of-00008.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e864627281171ce504450da0ad8ccde3d0f0436c80defbb558d8c8abc670cce0
3
- size 4957926072
 
 
 
 
model-00007-of-00008.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:937ca3b6eb37ab72e73efaca207f4841fc0f5d3a49eaa737dd59bdc0c50266f2
3
- size 4957926064
 
 
 
 
model-00008-of-00008.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fdb93b5bd306b318fedac04eeb26133332eebf9354dff87348ade9e2bdb53f7
3
- size 2351018392
 
 
 
 
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff