Hugging Face's logo

li-muyang
/
zephyr-7b-dpo-full

Text Generation
Transformers
TensorBoard
Safetensors
mistral
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Model card Files Metrics Community
li-muyang commited on
Commit
780dadf
·
verified ·
1 Parent(s): a13d0f6

Training in progress, epoch 0

Browse files
Files changed (9) hide show
  1. config.json +4 -4
  2. model-00001-of-00003.safetensors +2 -2
  3. model-00002-of-00003.safetensors +1 -1
  4. model-00003-of-00003.safetensors +2 -2
  5. model.safetensors.index.json +1 -1
  6. tokenizer.json +0 -0
  7. tokenizer.model +2 -2
  8. tokenizer_config.json +0 -0
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "data/zephyr-7b-sft-1e/checkpoint-900",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
@@ -17,11 +17,11 @@
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
  "rms_norm_eps": 1e-05,
20
- "rope_theta": 10000.0,
21
- "sliding_window": 4096,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.45.2",
25
  "use_cache": false,
26
- "vocab_size": 32000
27
  }
 
1
  {
2
+ "_name_or_path": "data/mistralv3-7b-sft-1e/checkpoint-400",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
 
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
  "rms_norm_eps": 1e-05,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.45.2",
25
  "use_cache": false,
26
+ "vocab_size": 32768
27
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf52ea0f2adadab124cf39a02cb9156455c90b814aae98b1065389f154b9d450
3
- size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30cc640382b2a2d9d11bacac2d8beddbfb7f8bf0c5b06338768ed1d05be78552
3
+ size 4949453792
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ae08d3bf0eede796a07d85f64f904d5ce71413ccfa9251e14ff4a9874db1f2e
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc99e87b77f4069044484b5bbcc321390f108b7c97dd9dd1039271d2573cefe5
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d58b809d654eed826b4363ca621641333dd920300cc197ae6825e864e6d592
3
- size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a76bb81cacb279718983ba44515b65d40a18aafd8b4fb16f777ab0d714058419
3
+ size 4546807800
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 14483464192
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00003-of-00003.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 14496047104
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00003-of-00003.safetensors",
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9e556f0d5cf2058bb632ea349981793e5df1e87d924f035ced98f1fe5b8c112
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931a170b477a20f89b4f587e9a9f4a5c46b387ea30ac53c397bdaa6125e407b3
3
  size 7672