Hugging Face's logo

Annuvin
/
EXAONE-3.0-7.8B-Instruct-Llamafied-6.5bpw-h8-exl2

llama
exl2
Model card Files Community
Annuvin commited on
Commit
f837db5
·
verified ·
1 Parent(s): 3ed4ca5

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +39 -39
  2. generation_config.json +7 -7
  3. measurement.json +0 -0
  4. special_tokens_map.json +30 -30
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +0 -0
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,40 +1,40 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 361,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 4096,
14
- "mlp_bias": false,
15
- "model_type": "llama",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 32,
18
- "num_key_value_heads": 8,
19
- "pad_token_id": 0,
20
- "pretraining_tp": 1,
21
- "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
23
- "rope_theta": 500000.0,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "float16",
26
- "transformers_version": "4.44.0",
27
- "use_cache": true,
28
- "vocab_size": 102400,
29
- "quantization_config": {
30
- "quant_method": "exl2",
31
- "version": "0.1.8",
32
- "bits": 6.5,
33
- "head_bits": 8,
34
- "calibration": {
35
- "rows": 115,
36
- "length": 2048,
37
- "dataset": "(default)"
38
- }
39
- }
40
  }
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 361,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 4096,
14
+ "mlp_bias": false,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "bits": 6.5,
23
+ "calibration": {
24
+ "dataset": "(default)",
25
+ "length": 2048,
26
+ "rows": 115
27
+ },
28
+ "head_bits": 8,
29
+ "quant_method": "exl2",
30
+ "version": "0.1.8"
31
+ },
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "float16",
37
+ "transformers_version": "4.44.0",
38
+ "use_cache": true,
39
+ "vocab_size": 102400
40
  }
generation_config.json CHANGED
@@ -1,7 +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": "4.44.0"
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": "4.44.0"
7
+ }
measurement.json CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,30 +1,30 @@
1
- {
2
- "bos_token": {
3
- "content": "[BOS]",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "[|endofturn|]",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "[PAD]",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "[UNK]",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[|endofturn|]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
vocab.json CHANGED
The diff for this file is too large to render. See raw diff