Hugging Face's logo

pilancilab
/
CALDERA-compressed-models

Model card Files Community
nsagan commited on
Commit
d4812c1
·
1 Parent(s): f3b8098

Add Llama-2-7b Rank 128 and Rank 64 models

Browse files
Files changed (14) hide show
  1. Llama-2-7b-2Bit-4BitFactors-Rank128/caldera-rank-128-4B-factors-downdate-RHT-ft.pt +3 -0
  2. Llama-2-7b-2Bit-4BitFactors-Rank128/caldera-rank-128-4B-factors-downdate-no-RHT-ft.pt +3 -0
  3. Llama-2-7b-2Bit-4BitFactors-Rank128/config.json +28 -0
  4. Llama-2-7b-2Bit-4BitFactors-Rank128/generation_config.json +10 -0
  5. Llama-2-7b-2Bit-4BitFactors-Rank128/special_tokens_map.json +23 -0
  6. Llama-2-7b-2Bit-4BitFactors-Rank128/tokenizer.json +0 -0
  7. Llama-2-7b-2Bit-4BitFactors-Rank128/tokenizer_config.json +41 -0
  8. Llama-2-7b-2Bit-4BitFactors-Rank64/caldera-rank-64-4B-factors-downdate-RHT-ft.pt +3 -0
  9. Llama-2-7b-2Bit-4BitFactors-Rank64/caldera-rank-64-4B-factors-downdate-no-RHT-ft.pt +3 -0
  10. Llama-2-7b-2Bit-4BitFactors-Rank64/config.json +28 -0
  11. Llama-2-7b-2Bit-4BitFactors-Rank64/generation_config.json +10 -0
  12. Llama-2-7b-2Bit-4BitFactors-Rank64/special_tokens_map.json +23 -0
  13. Llama-2-7b-2Bit-4BitFactors-Rank64/tokenizer.json +0 -0
  14. Llama-2-7b-2Bit-4BitFactors-Rank64/tokenizer_config.json +41 -0
Llama-2-7b-2Bit-4BitFactors-Rank128/caldera-rank-128-4B-factors-downdate-RHT-ft.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248cbd8371e258eed6704206f4326287993c4f6645e9dae8966e915d59fe4895
3
+ size 4256946627
Llama-2-7b-2Bit-4BitFactors-Rank128/caldera-rank-128-4B-factors-downdate-no-RHT-ft.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deb9c107f9a37da42e913e1ddf0c6836a1b663c3501f3464d59743abcd5e122f
3
+ size 4257013656
Llama-2-7b-2Bit-4BitFactors-Rank128/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.39.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
Llama-2-7b-2Bit-4BitFactors-Rank128/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.39.1"
10
+ }
Llama-2-7b-2Bit-4BitFactors-Rank128/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Llama-2-7b-2Bit-4BitFactors-Rank128/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Llama-2-7b-2Bit-4BitFactors-Rank128/tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
Llama-2-7b-2Bit-4BitFactors-Rank64/caldera-rank-64-4B-factors-downdate-RHT-ft.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06df9b99e27ef6c71268a628f1f865a0f9dfcd85d2400af584c403dc2a64d076
3
+ size 3130904124
Llama-2-7b-2Bit-4BitFactors-Rank64/caldera-rank-64-4B-factors-downdate-no-RHT-ft.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e7675248a52f7eae2c8145c5dd09f6510bef5d75c01388ad6bd6103912c34f
3
+ size 3130926609
Llama-2-7b-2Bit-4BitFactors-Rank64/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.39.1",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
Llama-2-7b-2Bit-4BitFactors-Rank64/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 4096,
6
+ "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
+ "transformers_version": "4.39.1"
10
+ }
Llama-2-7b-2Bit-4BitFactors-Rank64/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Llama-2-7b-2Bit-4BitFactors-Rank64/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
Llama-2-7b-2Bit-4BitFactors-Rank64/tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }