Update models
Browse files- .gitattributes +13 -0
- EXAONE-3.5-2.4B-Instruct-Q2_K.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q4_0.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q5_0.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q6_K.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-Q8_0.gguf +3 -0
- EXAONE-3.5-2.4B-Instruct-f16.gguf +3 -0
- config.json +39 -0
.gitattributes
CHANGED
@@ -33,3 +33,16 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
EXAONE-3.5-2.4B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
EXAONE-3.5-2.4B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
EXAONE-3.5-2.4B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
EXAONE-3.5-2.4B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
EXAONE-3.5-2.4B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
EXAONE-3.5-2.4B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
EXAONE-3.5-2.4B-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3d9d5dd8b15e6bbd5940343a125c63366cc13cfb4b8529a50f2e3017bbe8c9
|
3 |
+
size 1010442976
|
EXAONE-3.5-2.4B-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cfffc05e03da4f1d0a48872158a2c602ece6f6d485cd0ec6448a490e10ba1c9
|
3 |
+
size 1345982176
|
EXAONE-3.5-2.4B-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbeef3ba353c858a91e90048764d38508a372abe7c9240c9fe4ebf96b0745caa
|
3 |
+
size 1249152736
|
EXAONE-3.5-2.4B-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e32ad19c6fdaf36fa0272f45235434c82640d922d746fd1c1e638681e8f2743
|
3 |
+
size 1140695776
|
EXAONE-3.5-2.4B-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92ce4ea3b862535505d0dd17fff28fbdd72c6dd7ca63725ff75af96074c789f0
|
3 |
+
size 1425316576
|
EXAONE-3.5-2.4B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5568f285721bb1ac76a74c11e5d611fb08e328d40ce611463324993798c248db
|
3 |
+
size 1497462496
|
EXAONE-3.5-2.4B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:536a81b0be5581093a4990136bc9757e28955d76c5114ef820529c643fd8caee
|
3 |
+
size 1433017056
|
EXAONE-3.5-2.4B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2d125b6dabceb10da919f0b46bfaedd4346576274bdefbdfb767df56a2523d0
|
3 |
+
size 1693194976
|
EXAONE-3.5-2.4B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9569a651d5225b473b188b5d302e0e9615883b97f553bf3b4ea17d8f65ec6929
|
3 |
+
size 1730361056
|
EXAONE-3.5-2.4B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf7152d02d2017768775ce4579be83411f149d7209438af6d6b121e72c1211a0
|
3 |
+
size 1693194976
|
EXAONE-3.5-2.4B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28b856a2a71bb50e84bbc2199d807e41a478996236ae2bf23dd88be3c4290e8a
|
3 |
+
size 1977815776
|
EXAONE-3.5-2.4B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:890bdfe963106c073f8e7b4260df488f86d2776bb02f0fe45bdb731964482395
|
3 |
+
size 2560318176
|
EXAONE-3.5-2.4B-Instruct-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:011c4f713560f2a5d57d5ba3e601d2873f27c2fb51c8677f991298feec1208fc
|
3 |
+
size 4815166176
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_function": "silu",
|
3 |
+
"architectures": [
|
4 |
+
"ExaoneForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "configuration_exaone.ExaoneConfig",
|
9 |
+
"AutoModelForCausalLM": "modeling_exaone.ExaoneForCausalLM",
|
10 |
+
"AutoModelForSequenceClassification": "modeling_exaone.ExaoneForSequenceClassification"
|
11 |
+
},
|
12 |
+
"bos_token_id": 1,
|
13 |
+
"embed_dropout": 0.0,
|
14 |
+
"eos_token_id": 361,
|
15 |
+
"head_dim": 80,
|
16 |
+
"hidden_size": 2560,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 7168,
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"max_position_embeddings": 32768,
|
21 |
+
"model_type": "exaone",
|
22 |
+
"num_attention_heads": 32,
|
23 |
+
"num_key_value_heads": 8,
|
24 |
+
"num_layers": 30,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"rope_scaling": {
|
27 |
+
"factor": 8.0,
|
28 |
+
"high_freq_factor": 4.0,
|
29 |
+
"low_freq_factor": 1.0,
|
30 |
+
"original_max_position_embeddings": 8192,
|
31 |
+
"rope_type": "llama3"
|
32 |
+
},
|
33 |
+
"rope_theta": 1000000,
|
34 |
+
"tie_word_embeddings": true,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.43.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 102400
|
39 |
+
}
|