Hugging Face's logo

Pamzyy
/
testcode

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
Pamzyy commited on
Commit
6e70d7c
·
verified ·
1 Parent(s): 29840b7

Training in progress, step 5

Browse files
Files changed (5) hide show
  1. config.json +2 -2
  2. model-00001-of-00007.safetensors +1 -1
  3. model-00007-of-00007.safetensors +1 -1
  4. tokenizer_config.json +1 -8
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./results/checkpoint-35",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -31,6 +31,6 @@
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.47.1",
34
- "use_cache": false,
35
  "vocab_size": 138626
36
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.47.1",
34
+ "use_cache": true,
35
  "vocab_size": 138626
36
  }
model-00001-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c639cca74f3e21d0d21638ee1f69eedbe280e46c8f61380e17d96f8a7b54808
3
  size 4989259264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ebfae5b8af8f447067dbedf26bc342f37b5c13f8b716236fc5a44ff83e5ba7
3
  size 4989259264
model-00007-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:704de3a6018eb9c6f697e4c7127e3abefa57f368847fcd4bfdda2e02a00bbec0
3
  size 2741060264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80d89a79f5f4cdf17c2f149173b6ae2588b1ed0d2987bb36aeb5c3d9afedb81e
3
  size 2741060264
tokenizer_config.json CHANGED
@@ -2053,18 +2053,11 @@
2053
  "clean_up_tokenization_spaces": true,
2054
  "eos_token": "<|end_of_text|>",
2055
  "extra_special_tokens": {},
2056
- "max_length": 512,
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
2060
  ],
2061
  "model_max_length": 131072,
2062
- "pad_to_multiple_of": null,
2063
  "pad_token": "<|end_of_text|>",
2064
- "pad_token_type_id": 0,
2065
- "padding_side": "right",
2066
- "stride": 0,
2067
- "tokenizer_class": "PreTrainedTokenizerFast",
2068
- "truncation_side": "right",
2069
- "truncation_strategy": "longest_first"
2070
  }
 
2053
  "clean_up_tokenization_spaces": true,
2054
  "eos_token": "<|end_of_text|>",
2055
  "extra_special_tokens": {},
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
 
2061
  "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
 
2063
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:389a43ba2a03dd5d713a6c9be5f780cf98e0d7ffc7ede138d278b385d874f6f9
3
- size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a908ade51cd9b861382462385f51c098680a2e9c61e12916af6dea0e00d0e95
3
+ size 5304