Hugging Face's logo

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

Text Generation
Transformers
TensorBoard
Safetensors
mistral
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files Metrics Community
li-muyang commited on
Commit
1c9fa3a
·
verified ·
1 Parent(s): 9c62a22

Training in progress, step 100

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": "mistralai/Mistral-7B-v0.3",
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": "mistralai/Mistral-7B-v0.1",
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 sha256:9a2b59512e2b2bec9718a906a880c173c3d83ac81d69c189f6d531eaf3ca0508
3
- size 4949453792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a2ba716a5698e4498e69020aae4e3018ae58b738309aa815ee0ed6e6107d3c
3
+ size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bd161ee05f70d31a911a572b3b6aac67def6470f64c1dbd0d4e9d537b81dbcf
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4dc771b7f6f23db6d2e0facf09c69be083eca5c0afe158936dc172451351881
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:e0798a873fbb468e76da6d6c65dfe6cb6fe832b79a0ddaed9e84fc3f9a982277
3
- size 4546807800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3bf7ec9d54cfd4dffe258d0a7d497b429f00ccf060704a716f1b0608b9d7d7
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:d436f50c1e6fe826dced4a6d00e29427889641d26e400ec8b18fda6737429dcc
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55dc64f1aa501eba0b5c6cc0c82061cc9c2168b0fda9f2a9a81f1e12f7fbec25
3
  size 7032