n1ck-guo commited on
Commit
63a4807
1 Parent(s): bfe7c7c

Signed-off-by: n1ck-guo <heng.guo@intel.com>

config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/models/falcon3-3B",
3
+ "activation": "swiglu",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 11,
10
+ "eos_token_id": 11,
11
+ "head_dim": 256,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3072,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 9216,
16
+ "max_position_embeddings": 4096,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 22,
21
+ "num_key_value_heads": 4,
22
+ "parallel_attn": false,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "amp": true,
26
+ "autoround_version": "0.4.2",
27
+ "backend": "auto_round:gptq:exllamav2",
28
+ "batch_size": 8,
29
+ "bits": 4,
30
+ "data_type": "int",
31
+ "dataset": "NeelNanda/pile-10k",
32
+ "enable_minmax_tuning": true,
33
+ "enable_norm_bias_tuning": false,
34
+ "enable_quanted_input": true,
35
+ "gradient_accumulate_steps": 1,
36
+ "group_size": 128,
37
+ "iters": 2000,
38
+ "low_gpu_mem_usage": false,
39
+ "lr": 0.0005,
40
+ "minmax_lr": 0.0005,
41
+ "nsamples": 512,
42
+ "quant_method": "intel/auto-round",
43
+ "scale_dtype": "torch.float16",
44
+ "seqlen": 2048,
45
+ "sym": true,
46
+ "to_quant_block_names": null
47
+ },
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000042,
51
+ "tie_word_embeddings": false,
52
+ "torch_dtype": "float16",
53
+ "transformers_version": "4.47.0",
54
+ "use_cache": true,
55
+ "vocab_size": 131072
56
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 11,
4
+ "eos_token_id": 11,
5
+ "transformers_version": "4.47.0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8f915a4dedb6f1f52f67a2bdded9c78cf02f538be4ac9adac4060432c4b8467
3
+ size 2871810080
quantization_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "sym": true,
5
+ "data_type": "int",
6
+ "enable_quanted_input": true,
7
+ "enable_minmax_tuning": true,
8
+ "seqlen": 2048,
9
+ "batch_size": 8,
10
+ "scale_dtype": "torch.float16",
11
+ "lr": 0.0005,
12
+ "minmax_lr": 0.0005,
13
+ "gradient_accumulate_steps": 1,
14
+ "iters": 2000,
15
+ "amp": true,
16
+ "nsamples": 512,
17
+ "low_gpu_mem_usage": false,
18
+ "to_quant_block_names": null,
19
+ "enable_norm_bias_tuning": false,
20
+ "dataset": "NeelNanda/pile-10k",
21
+ "autoround_version": "0.4.2",
22
+ "quant_method": "intel/auto-round",
23
+ "backend": "auto_round:gptq:exllamav2"
24
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>EMAIL_ADDRESS<<",
12
+ ">>IP_ADDRESS<<",
13
+ "<|startoftext|>",
14
+ ">>IP_ADDRESS_0<<",
15
+ ">>IP_ADDRESS_1<<",
16
+ ">>IP_ADDRESS_2<<",
17
+ ">>IP_ADDRESS_3<<",
18
+ ">>IP_ADDRESS_4<<",
19
+ ">>IP_ADDRESS_5<<",
20
+ ">>IP_ADDRESS_6<<",
21
+ ">>IP_ADDRESS_7<<",
22
+ ">>IP_ADDRESS_8<<",
23
+ ">>IP_ADDRESS_9<<",
24
+ ">>PASSWORD<<",
25
+ ">>KEY<<"
26
+ ],
27
+ "eos_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff