Upload ExaoneForCausalLM
Browse files- config.json +48 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct",
|
3 |
+
"activation_function": "silu",
|
4 |
+
"architectures": [
|
5 |
+
"ExaoneForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--configuration_exaone.ExaoneConfig",
|
10 |
+
"AutoModelForCausalLM": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--modeling_exaone.ExaoneForCausalLM",
|
11 |
+
"AutoModelForSequenceClassification": "LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct--modeling_exaone.ExaoneForSequenceClassification"
|
12 |
+
},
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"embed_dropout": 0.0,
|
15 |
+
"eos_token_id": 361,
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 14336,
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"max_position_embeddings": 4096,
|
21 |
+
"model_type": "exaone",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"num_layers": 32,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"quantization_config": {
|
27 |
+
"_load_in_4bit": true,
|
28 |
+
"_load_in_8bit": false,
|
29 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
30 |
+
"bnb_4bit_quant_storage": "uint8",
|
31 |
+
"bnb_4bit_quant_type": "nf4",
|
32 |
+
"bnb_4bit_use_double_quant": true,
|
33 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
34 |
+
"llm_int8_has_fp16_weight": false,
|
35 |
+
"llm_int8_skip_modules": null,
|
36 |
+
"llm_int8_threshold": 6.0,
|
37 |
+
"load_in_4bit": true,
|
38 |
+
"load_in_8bit": false,
|
39 |
+
"quant_method": "bitsandbytes"
|
40 |
+
},
|
41 |
+
"rope_scaling": null,
|
42 |
+
"rope_theta": 500000.0,
|
43 |
+
"tie_word_embeddings": false,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.47.0.dev0",
|
46 |
+
"use_cache": false,
|
47 |
+
"vocab_size": 102400
|
48 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 361,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.47.0.dev0"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e2165b76848345d580d7ad4ab9639b2d0e30116d1c957cfdf9a82e1dd60bac6
|
3 |
+
size 4993932556
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf379ffb35e7b432525ba88286c4ff744ddc18b2c5079bd1fc24050e26da4472
|
3 |
+
size 1963446366
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|