config.json CHANGED
@@ -6,11 +6,7 @@
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 128000,
8
  "dtype": "float16",
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
  "head_dim": 128,
15
  "hidden_act": "silu",
16
  "hidden_size": 4096,
@@ -33,7 +29,7 @@
33
  },
34
  "rope_theta": 500000.0,
35
  "tie_word_embeddings": false,
36
- "transformers_version": "4.57.2",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 128000,
8
  "dtype": "float16",
9
+ "eos_token_id": 128001,
 
 
 
 
10
  "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
 
29
  },
30
  "rope_theta": 500000.0,
31
  "tie_word_embeddings": false,
32
+ "transformers_version": "4.57.3",
33
  "use_cache": true,
34
  "vocab_size": 128256
35
  }
generation_config.json CHANGED
@@ -1,12 +1,9 @@
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.57.2"
12
  }
 
1
  {
2
+ "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
+ "eos_token_id": 128001,
 
 
 
 
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.57.3"
9
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac8863800d625511455e924e46fb660efa458a293a1cd278fcaa316988da3e42
3
  size 4976698592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c885e1d84417cb182a5c84245adb124b87b82cfb0ccac6b3e69223989d35621
3
  size 4976698592
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14ad43288142c7fa0cde7787ce13369d099fb780885bd9044f2917841c87b1ec
3
  size 4999802616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7648099ddb746d2e72afd5962f7b5b02c2d8ef2ea2535532247393d300948876
3
  size 4999802616
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e3a0683911ecc8bc81b6356ac076b7d59dfa6ece0e98b79dfa4dd7005e5c912
3
  size 4915916080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b381410c7699d4dfb54231865a1fe0f61e69e4bc8ec88354cff211cd15a7b3
3
  size 4915916080
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:013bc9e3d5d06232d8a358ad3cd323b732255d31e2debe3bf0c6325b88110ae0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a016d2dbcb9e7f2a11285f7b4514e89264f14d579cb7aafbf4192172723e34
3
  size 1168138808
special_tokens_map.json CHANGED
@@ -7,11 +7,11 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|eot_id|>"
17
  }
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|end_of_text|>"
17
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c70650b4236027dc8db4abca6b918783a8ed2ee38cd69142f6dbbeb5945f876f
3
- size 17210195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d4fd2d4afa82d8a7dadae3490fdc20b26f06e32cec78a8dc96521b4dc79038
3
+ size 17210200
tokenizer_config.json CHANGED
@@ -2051,13 +2051,13 @@
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
  "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|eot_id|>",
2055
  "extra_special_tokens": {},
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
  "model_max_length": 131072,
2061
- "pad_token": "<|eot_id|>",
2062
  "tokenizer_class": "PreTrainedTokenizerFast"
2063
  }
 
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
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
  }