Hugging Face's logo

nm-testing
/
tinyllama-oneshot-w8a8-dynamic-token-v2

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
8-bit precision
compressed-tensors
Model card Files
xet
 Community
sadkins65 commited on
Commit
aaab418
·
verified ·
1 Parent(s): 7e0f213

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +75 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. recipe.yaml +10 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +42 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "compression_config": {
10
+ "quantization_config": {
11
+ "config_groups": {
12
+ "group_0": {
13
+ "input_activations": {
14
+ "block_structure": null,
15
+ "dynamic": true,
16
+ "group_size": null,
17
+ "num_bits": 8,
18
+ "observer": "memoryless",
19
+ "observer_kwargs": {},
20
+ "strategy": "token",
21
+ "symmetric": true,
22
+ "type": "int"
23
+ },
24
+ "output_activations": null,
25
+ "targets": [
26
+ "Linear"
27
+ ],
28
+ "weights": {
29
+ "block_structure": null,
30
+ "dynamic": false,
31
+ "group_size": null,
32
+ "num_bits": 8,
33
+ "observer": "minmax",
34
+ "observer_kwargs": {},
35
+ "strategy": "tensor",
36
+ "symmetric": true,
37
+ "type": "int"
38
+ }
39
+ }
40
+ },
41
+ "format": "int-quantized",
42
+ "global_compression_ratio": 1.2391304140415598,
43
+ "ignore": [
44
+ "lm_head"
45
+ ],
46
+ "quant_method": "sparseml",
47
+ "quantization_status": "frozen"
48
+ },
49
+ "sparsity_config": {
50
+ "format": "dense",
51
+ "global_sparsity": 7.819320427273134,
52
+ "registry_requires_subclass": false,
53
+ "sparsity_structure": "unstructured"
54
+ }
55
+ },
56
+ "eos_token_id": 2,
57
+ "hidden_act": "silu",
58
+ "hidden_size": 2048,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 5632,
61
+ "max_position_embeddings": 2048,
62
+ "model_type": "llama",
63
+ "num_attention_heads": 32,
64
+ "num_hidden_layers": 22,
65
+ "num_key_value_heads": 4,
66
+ "pretraining_tp": 1,
67
+ "rms_norm_eps": 1e-05,
68
+ "rope_scaling": null,
69
+ "rope_theta": 10000.0,
70
+ "tie_word_embeddings": false,
71
+ "torch_dtype": "bfloat16",
72
+ "transformers_version": "4.40.0",
73
+ "use_cache": true,
74
+ "vocab_size": 32000
75
+ }
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": "4.40.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416a7f8569151f839a863e5d4a8424f784e97dcdf77fd074aabdf46b61c10cd9
3
+ size 1231252556
recipe.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ quant_stage:
2
+ quant_modifiers:
3
+ GPTQModifier:
4
+ sequential_update: false
5
+ ignore: [lm_head]
6
+ config_groups:
7
+ group_0:
8
+ weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
9
+ input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}
10
+ 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_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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 %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }