Update models
Browse files- .gitattributes +13 -0
- EXAONE-Deep-2.4B-Q2_K.gguf +3 -0
- EXAONE-Deep-2.4B-Q3_K_L.gguf +3 -0
- EXAONE-Deep-2.4B-Q3_K_M.gguf +3 -0
- EXAONE-Deep-2.4B-Q3_K_S.gguf +3 -0
- EXAONE-Deep-2.4B-Q4_0.gguf +3 -0
- EXAONE-Deep-2.4B-Q4_K_M.gguf +3 -0
- EXAONE-Deep-2.4B-Q4_K_S.gguf +3 -0
- EXAONE-Deep-2.4B-Q5_0.gguf +3 -0
- EXAONE-Deep-2.4B-Q5_K_M.gguf +3 -0
- EXAONE-Deep-2.4B-Q5_K_S.gguf +3 -0
- EXAONE-Deep-2.4B-Q6_K.gguf +3 -0
- EXAONE-Deep-2.4B-Q8_0.gguf +3 -0
- EXAONE-Deep-2.4B-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-Deep-2.4B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
EXAONE-Deep-2.4B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
EXAONE-Deep-2.4B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
EXAONE-Deep-2.4B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
EXAONE-Deep-2.4B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
EXAONE-Deep-2.4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
EXAONE-Deep-2.4B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
EXAONE-Deep-2.4B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
EXAONE-Deep-2.4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
EXAONE-Deep-2.4B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
EXAONE-Deep-2.4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
EXAONE-Deep-2.4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
EXAONE-Deep-2.4B-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
EXAONE-Deep-2.4B-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:429c28b27a9e21aba92e3004ae339e5176be906e46708c863694df9355388c6a
|
3 |
+
size 1010443392
|
EXAONE-Deep-2.4B-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44dc88716186cc867f6a11f4afe66bbc7c2cecdb1b03a1e0f853078f970b849a
|
3 |
+
size 1345982592
|
EXAONE-Deep-2.4B-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5479d394c74088ad74e0895d92bcb9b73fd77103919a342092eefbe6586e71df
|
3 |
+
size 1249153152
|
EXAONE-Deep-2.4B-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90be88f4c26df9afce5333358ba403017ded0ffbf36e2bd5d10b028d53c94675
|
3 |
+
size 1140696192
|
EXAONE-Deep-2.4B-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab1d6a180aa71378a2f478963291722bb28d94397165b6454efc7ce28850edd4
|
3 |
+
size 1425316992
|
EXAONE-Deep-2.4B-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3af6cb2a8c18b1378b7ccebd0107551e1c72c5710288c89d09ed28ea625c233
|
3 |
+
size 1497462912
|
EXAONE-Deep-2.4B-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf22dbb60cf570a50c260e5e9b5b675052c2fc4fe8a2d6d4cf020cf381835c7f
|
3 |
+
size 1433017472
|
EXAONE-Deep-2.4B-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc5011bbf1501c8f3acb436d13e029bd7054c72a2446b991f8cd3ad73b23bdc7
|
3 |
+
size 1693195392
|
EXAONE-Deep-2.4B-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:046dd829e7ad589a0b29e685fd003b2e8808008cd6015215eaf76bd56a2f2d07
|
3 |
+
size 1730361472
|
EXAONE-Deep-2.4B-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee794ccfbe1d46cb0b145d5042bb087e32d14eaa4eb714f57501f9167d5f85b4
|
3 |
+
size 1693195392
|
EXAONE-Deep-2.4B-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc8e3fe002a61c947a103026ec010b13fe91fc08e61e0435e856b5ae6d03c2b7
|
3 |
+
size 1977816192
|
EXAONE-Deep-2.4B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e0b1a8b4b1e5036c1c077fb7efbe86176d8cb286633b4824206699d95ae4f74
|
3 |
+
size 2560318592
|
EXAONE-Deep-2.4B-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e56d0455c99fda694a3f5090176c5010560755390217bc04d341ebdf9b328b18
|
3 |
+
size 4815166592
|
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": "bfloat16",
|
36 |
+
"transformers_version": "4.43.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 102400
|
39 |
+
}
|