Update models
Browse files- .gitattributes +13 -0
- EXAONE-3.5-7.8B-Instruct-Q2_K.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_0.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_0.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q6_K.gguf +3 -0
- EXAONE-3.5-7.8B-Instruct-Q8_0.gguf +3 -0
- EXAONE-3.5-7.8B-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-3.5-7.8B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
EXAONE-3.5-7.8B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
EXAONE-3.5-7.8B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
EXAONE-3.5-7.8B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
EXAONE-3.5-7.8B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
EXAONE-3.5-7.8B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
EXAONE-3.5-7.8B-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae27fa0e8f3b91081ce91b8241248a7a99974cbcce21a27a6fdf9a9c50504d2
|
3 |
+
size 3053868960
|
EXAONE-3.5-7.8B-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3beba6701da05cbfca258d8e2f910857c1f9d7243a5b722f613cfb27cab84326
|
3 |
+
size 4185937824
|
EXAONE-3.5-7.8B-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb1cbd4c0333f8288a8dca35c6fbe4a6bfbc2e25d4d568f883a927eb0d59d1ce
|
3 |
+
size 3882899360
|
EXAONE-3.5-7.8B-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c952a90d64c85c5e4370e61791143211708ca9a923c8b054ba8f0984e8b05416
|
3 |
+
size 3528480672
|
EXAONE-3.5-7.8B-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f01dd5cd9a793422a81d65a581f40d5e251906ea05e59cfa80a29a029e3da70b
|
3 |
+
size 4511127456
|
EXAONE-3.5-7.8B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f6d1fdbe388c15b038150706c851591612252bf679dbeca6359ea6dbe78e3f9
|
3 |
+
size 4770650016
|
EXAONE-3.5-7.8B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2eff7af76a22b4eb6128c1947cfc1ca6c2516a5aa130bc5bc50d8893120a7f9
|
3 |
+
size 4542584736
|
EXAONE-3.5-7.8B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a84f4c6e41670762f924ce77880f661f0a0f758a77213a3dc8600f6522b2f3d
|
3 |
+
size 5435971488
|
EXAONE-3.5-7.8B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64a544a98a8a528bab6ad1605c811b9dd6ffedc1b8ee7cdda9f7d7f4f5d33c5f
|
3 |
+
size 5569664928
|
EXAONE-3.5-7.8B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:203f8674c835d1139abe751f25f8ec4a1f7c20d93fed6917780d39cf7ea1d77c
|
3 |
+
size 5435971488
|
EXAONE-3.5-7.8B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15e4d1d3ff7c426c9c5e8bb5ccf028cf94d06e1178b6d054f2ad20d1754ef9ca
|
3 |
+
size 6418618272
|
EXAONE-3.5-7.8B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8032de629508aed6fd50c8c2ea0055a5b6d284fe63c1fbe0b815e97af53e761
|
3 |
+
size 8312084384
|
EXAONE-3.5-7.8B-Instruct-f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c9a65c06234a83316aa40ea490e20139ddb5bce58149c3056ac145a06a19231
|
3 |
+
size 15641630624
|
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": 128,
|
16 |
+
"hidden_size": 4096,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 14336,
|
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": 32,
|
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": 1000000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.43.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 102400
|
39 |
+
}
|