Hugging Face's logo

kangqi-ni
/
Mistral-7B-Instruct-v0.2_bio-tutor_dpo

Text Generation
Transformers
Safetensors
English
mistral
dpo
biology
education
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Kevin Ni commited on
Commit
cbad772
•
1 Parent(s): 7c5c4d9

update the model

Browse files
Files changed (8) hide show
  1. config.json +3 -2
  2. generation_config.json +1 -1
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +1 -0
  8. training_args.bin +2 -2
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "/data/kn22/spock_bio/spock_bio_Mistral-7B-Instruct-v0.2_r1",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
 
9
  "hidden_act": "silu",
10
  "hidden_size": 4096,
11
  "initializer_range": 0.02,
@@ -20,7 +21,7 @@
20
  "sliding_window": null,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.36.2",
24
  "use_cache": true,
25
  "vocab_size": 32000
26
  }
 
1
  {
2
+ "_name_or_path": "/data1/kn22/spock_bio/spock_bio_Mistral-7B-Instruct-v0.2_1",
3
  "architectures": [
4
  "MistralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 128,
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
 
21
  "sliding_window": null,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.45.1",
25
  "use_cache": true,
26
  "vocab_size": 32000
27
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.36.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.45.1"
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b1c142c09f3a3fb314879d6d9691fa516e60e97fb965b534af3833b70409283
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e02ff422dd58253ba53291b08b4ce1f941108df5eb5132005b5dfc194dfc053
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9798b5df4ab3c510a18906a9d9d8e770f943094c4ee823429211adb41278ea9b
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c9cf991cd1f27516a5eafa8566c25d0cbf8f103238600519f7d12391fb7c4b
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:c7a5b5947dfc845bdd86011c1239d5a7d6efe1e9c3dbf5b8121a12ea9f8b38c3
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7df2c440a07125d10e290d62eaacbb438263a0ff2387ef8cdb22abc49f85e43
3
  size 4540516344
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82f3c9a890782f6a1818a099577c14e2160520ad5ebcf2a4dd758209696b45c4
3
- size 5880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440d608da1fea92b8792670a3c79bab3cfaf4f67bb4b2b9f573384ff764d61f0
3
+ size 7352