sadkins65 commited on
Commit
c1500cf
1 Parent(s): ba12b89

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-intermediate-step-1431k-3T/snapshots/036fa4651240b9a1487f709833b9e4b96b4c1574",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "quantization_config": {
10
+ "config_groups": {
11
+ "group_0": {
12
+ "input_activations": {
13
+ "actorder": false,
14
+ "block_structure": null,
15
+ "dynamic": false,
16
+ "group_size": null,
17
+ "num_bits": 8,
18
+ "observer": "minmax",
19
+ "observer_kwargs": {},
20
+ "strategy": "tensor",
21
+ "symmetric": true,
22
+ "type": "int"
23
+ },
24
+ "output_activations": null,
25
+ "targets": [
26
+ "Linear"
27
+ ],
28
+ "weights": {
29
+ "actorder": false,
30
+ "block_structure": null,
31
+ "dynamic": false,
32
+ "group_size": null,
33
+ "num_bits": 8,
34
+ "observer": "minmax",
35
+ "observer_kwargs": {},
36
+ "strategy": "tensor",
37
+ "symmetric": true,
38
+ "type": "int"
39
+ }
40
+ }
41
+ },
42
+ "format": "int-quantized",
43
+ "global_compression_ratio": 1.4556212089295866,
44
+ "ignore": [
45
+ "lm_head"
46
+ ],
47
+ "kv_cache_scheme": null,
48
+ "quant_method": "compressed-tensors",
49
+ "quantization_status": "compressed",
50
+ "sparsity_config": {
51
+ "format": "dense",
52
+ "global_sparsity": 0.07819527963599099,
53
+ "registry_requires_subclass": false,
54
+ "sparsity_structure": "unstructured"
55
+ }
56
+ },
57
+ "eos_token_id": 2,
58
+ "hidden_act": "silu",
59
+ "hidden_size": 2048,
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 5632,
62
+ "max_position_embeddings": 2048,
63
+ "mlp_bias": false,
64
+ "model_type": "llama",
65
+ "num_attention_heads": 32,
66
+ "num_hidden_layers": 22,
67
+ "num_key_value_heads": 4,
68
+ "pretraining_tp": 1,
69
+ "rms_norm_eps": 1e-05,
70
+ "rope_scaling": null,
71
+ "rope_theta": 10000.0,
72
+ "tie_word_embeddings": false,
73
+ "torch_dtype": "bfloat16",
74
+ "transformers_version": "4.45.0.dev0",
75
+ "use_cache": true,
76
+ "vocab_size": 32000
77
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 2048,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.45.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b03a77828fdca417c2e3a418f3e4cc846e05c65fadab410692468dedac86f92
3
+ size 1231270112
recipe.yaml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ quant_stage:
2
+ quant_modifiers:
3
+ GPTQModifier:
4
+ ignore: [lm_head]
5
+ config_groups:
6
+ group_0:
7
+ weights: {num_bits: 8, strategy: tensor}
8
+ input_activations: {num_bits: 8, strategy: tensor}
9
+ targets: [Linear]
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": false,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "padding_side": "right",
39
+ "sp_model_kwargs": {},
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }