Hugging Face's logo

MLP-KTLim
/
llama-3-Korean-Bllossom-8B

Text Generation
Transformers
Safetensors
English
Korean
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
16
PerRing commited on
Commit
6b7fe0a
·
verified ·
1 Parent(s): a86d965

Upload LlamaForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +10 -4
  2. generation_config.json +2 -2
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "MLP-KTLim/elo_best_chat_model",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -11,7 +11,7 @@
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
@@ -19,11 +19,17 @@
19
  "num_key_value_heads": 8,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
 
 
 
 
 
 
23
  "rope_theta": 500000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.38.2",
27
  "use_cache": false,
28
  "vocab_size": 128256
29
  }
 
1
  {
2
+ "_name_or_path": "/raid/MLP/ELO/ELO_Llama_3.1_8b_chat_20per_trained_v3_new/checkpoint-2250",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
 
19
  "num_key_value_heads": 8,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.43.1",
33
  "use_cache": false,
34
  "vocab_size": 128256
35
  }
generation_config.json CHANGED
@@ -1,9 +1,9 @@
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
  "eos_token_id": 128001,
5
- "max_length": 4096,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
- "transformers_version": "4.38.2"
9
  }
 
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": "4.43.1"
9
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9944e18bf20e59bc58620774e1c3eab053ca49d427e3d001885159fb6757918
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ae45771de142fd00793d5ed7f2b83abc47d722122ebbf9db398ced768f9618
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:d8cbaf21a417633632191d7397de6296fe39b430590e959bc31106929ef6386f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f649d98bb6c827ce53af8c7f6f1f3e56104e37e99122f8e6514e529f9b9eb0
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d22999592630dbf84d3c3b925ac09f72a284eb4c4c0df9689f81d1426d4b438
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765fc20ce82727e970fe3cafa0814e3a524b685227bf826ede8cfc90f292e819
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:cf68e873db87d8a64407f07e26a95e43d00a6fc4dbd81ea184070a8def2a2e38
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54da2153afb998b62fa8c2b937bb3b277770d59709c82d848ee84413cff3f5c6
3
  size 1168138808