Hugging Face's logo

li-muyang
/
zephyr-8b-dpo-full

Text Generation
Transformers
Safetensors
llama
trl
dpo
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
li-muyang commited on
Commit
3a23ec3
·
verified ·
1 Parent(s): a214eb1

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. config.json +1 -1
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. tokenizer_config.json +0 -1
  7. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "data/zephyr-8b-sft-full/checkpoint-200",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "data/every_10/checkpoint-10",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e318d903a9f6f2b28fe96db450af7c31e0021f375f35458d703a7acd33c5737
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e32be3219c3dd57723e284056120524c969e7f426e20841bf490433c96fdf8f
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe606d9e7979d29184b1bb43f9546f9ead748b8c250570e1308ce4f14e71c770
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f844628950ae44f3c207b99e4f326c309a649d93269a7197b348db4e4e61d12e
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:574ba2370712531a3fd43656770f7edd50b93ee13587c1326c303f2957368501
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9108a1918448c7f84415d494a3385574c48dd1f843562057057af4127934f451
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ec2bc2c1f58b69d7ab8bda0a3aa077a857182a59dfed88741d6076396646159
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cde068468b763af4c06c74e4545a6d77ba079e5f516f8407ee2d2f52c330ca7
3
  size 1168138808
tokenizer_config.json CHANGED
@@ -2053,7 +2053,6 @@
2053
  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
2056
- "extra_special_tokens": {},
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
 
2053
  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|end_of_text|>",
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bbff2b19e92547aca26125e0b340ca9761c66ed75e0f57d01f436326f403c3c
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa78907d1bfe322f021090da16621656ff3e941ef59eaaacadff30d26ac8ba9
3
  size 7672