kelce commited on
Commit
e5f9ac6
1 Parent(s): 2231c8b

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- library_name: transformers
3
- tags: []
4
  ---
5
 
6
  # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
1
  ---
2
+ base_model: beomi/Llama-3-Open-Ko-8B
3
+ library_name: peft
4
  ---
5
 
6
  # Model Card for Model ID
 
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
+
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
 
196
 
197
  ## Model Card Contact
198
 
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beomi/Llama-3-Open-Ko-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": true,
22
+ "_load_in_8bit": false,
23
+ "bnb_4bit_compute_dtype": "float16",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 500000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.40.1",
41
+ "use_cache": false,
42
+ "vocab_size": 128256
43
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2347c565213aabc6d4da15048419927f0675996a7e7d2da998ed8448711b007
3
+ size 4998616884
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576963ed91630e0ebae3b2ec8978726c717161afff90fc5733af79d10a206efb
3
+ size 3240230300
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -13,11 +13,5 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "<|end_of_text|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
  }
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|end_of_text|>"
 
 
 
 
 
 
17
  }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa36f6b0341fe68707a210f0bb588747b0ea2f903e6ba91d779196a917171d9c
3
+ size 4984