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
xet
Metrics Community
li-muyang commited on
Commit
25623a4
·
verified ·
1 Parent(s): e6d0960

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/mistralv3-7b-sft-1e/checkpoint-300",
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": 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
  }
 
1
  {
2
+ "_name_or_path": "data/zephyr-7b-sft-lr1e-5/checkpoint-500",
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": 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
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e982290e2457289f3d1f5ccc8a0c223437826f11b542323ebe4a4dd87008fc71
3
- size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78cabdcd13d09a7055ad3ca2031f2ff2cff08c0c9bac54e4058deaf6762b5b9f
3
+ size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f05327b595ba7b4caecfba6c5b60d5928e16c22d940fa2affce93ef0b2180a66
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e2915c0ad35af94554eb8713f60084c18a7a893700c6af470faad3ff578e54
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:ce2c21c26ce2ab519aefaedd84b4890ee43f2f279d78d635ae3fd80240213223
3
- size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f260c24bdc2895b2643a47f657d6579a1c2da4a60489e452b607d2fc096165d0
3
+ size 4540516344
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 14496047104
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00003-of-00003.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 14483464192
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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
- size 587404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
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 sha256:61c72bfd3e42719eef1b6e23a06957b069d4c32ae3e8f02f25ae50fc97aab2a3
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a084647ba6c06903309d52c0f9562171fb21ab04270dff2d0bd2a32ccec2c1e5
3
  size 7672