Hugging Face's logo

skymizer
/
quantized-debug-models

GGUF
conversational
Model card Files
xet
 Community
elichen-skymizer commited on
Commit
19a0c4b
·
1 Parent(s): a4c3f57

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. hf/qwen3-0.6b-base-q3_k_m-dc-b10/config.json +116 -0
  2. hf/qwen3-0.6b-base-q3_k_m-dc-b10/generation_config.json +7 -0
  3. hf/qwen3-0.6b-base-q3_k_m/config.json +116 -0
  4. hf/qwen3-0.6b-base-q3_k_m/generation_config.json +7 -0
hf/qwen3-0.6b-base-q3_k_m-dc-b10/config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 151936,
3
+ "max_position_embeddings": 32768,
4
+ "hidden_size": 1024,
5
+ "intermediate_size": 3072,
6
+ "num_hidden_layers": 28,
7
+ "num_attention_heads": 16,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
+ "num_key_value_heads": 8,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "initializer_range": 0.02,
15
+ "rms_norm_eps": 9.999999974752427e-07,
16
+ "use_cache": true,
17
+ "rope_theta": 1000000.0,
18
+ "rope_scaling": null,
19
+ "attention_bias": false,
20
+ "attention_dropout": 0.0,
21
+ "layer_types": [
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "return_dict": true,
52
+ "output_hidden_states": false,
53
+ "torchscript": false,
54
+ "torch_dtype": "bfloat16",
55
+ "pruned_heads": {},
56
+ "tie_word_embeddings": true,
57
+ "chunk_size_feed_forward": 0,
58
+ "is_encoder_decoder": false,
59
+ "is_decoder": false,
60
+ "cross_attention_hidden_size": null,
61
+ "add_cross_attention": false,
62
+ "tie_encoder_decoder": false,
63
+ "architectures": [
64
+ "Qwen3ForCausalLM"
65
+ ],
66
+ "finetuning_task": null,
67
+ "id2label": {
68
+ "0": "LABEL_0",
69
+ "1": "LABEL_1"
70
+ },
71
+ "label2id": {
72
+ "LABEL_0": 0,
73
+ "LABEL_1": 1
74
+ },
75
+ "task_specific_params": null,
76
+ "problem_type": null,
77
+ "tokenizer_class": null,
78
+ "prefix": null,
79
+ "bos_token_id": 151643,
80
+ "pad_token_id": 151643,
81
+ "eos_token_id": 151643,
82
+ "sep_token_id": null,
83
+ "decoder_start_token_id": null,
84
+ "max_length": 20,
85
+ "min_length": 0,
86
+ "do_sample": false,
87
+ "early_stopping": false,
88
+ "num_beams": 1,
89
+ "num_beam_groups": 1,
90
+ "diversity_penalty": 0.0,
91
+ "temperature": 1.0,
92
+ "top_k": 50,
93
+ "top_p": 1.0,
94
+ "typical_p": 1.0,
95
+ "repetition_penalty": 1.0,
96
+ "length_penalty": 1.0,
97
+ "no_repeat_ngram_size": 0,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "bad_words_ids": null,
100
+ "num_return_sequences": 1,
101
+ "output_scores": false,
102
+ "return_dict_in_generate": false,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "remove_invalid_values": false,
106
+ "exponential_decay_length_penalty": null,
107
+ "suppress_tokens": null,
108
+ "begin_suppress_tokens": null,
109
+ "_name_or_path": "./models/",
110
+ "transformers_version": "4.55.0",
111
+ "model_type": "qwen3",
112
+ "_model_name_or_path": "Qwen3 0.6B Base",
113
+ "tf_legacy_loss": false,
114
+ "use_bfloat16": false,
115
+ "output_attentions": false
116
+ }
hf/qwen3-0.6b-base-q3_k_m-dc-b10/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "pad_token_id": 151643,
6
+ "transformers_version": "4.55.0"
7
+ }
hf/qwen3-0.6b-base-q3_k_m/config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 151936,
3
+ "max_position_embeddings": 32768,
4
+ "hidden_size": 1024,
5
+ "intermediate_size": 3072,
6
+ "num_hidden_layers": 28,
7
+ "num_attention_heads": 16,
8
+ "use_sliding_window": false,
9
+ "sliding_window": null,
10
+ "max_window_layers": 28,
11
+ "num_key_value_heads": 8,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "initializer_range": 0.02,
15
+ "rms_norm_eps": 9.999999974752427e-07,
16
+ "use_cache": true,
17
+ "rope_theta": 1000000.0,
18
+ "rope_scaling": null,
19
+ "attention_bias": false,
20
+ "attention_dropout": 0.0,
21
+ "layer_types": [
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "return_dict": true,
52
+ "output_hidden_states": false,
53
+ "torchscript": false,
54
+ "torch_dtype": "bfloat16",
55
+ "pruned_heads": {},
56
+ "tie_word_embeddings": true,
57
+ "chunk_size_feed_forward": 0,
58
+ "is_encoder_decoder": false,
59
+ "is_decoder": false,
60
+ "cross_attention_hidden_size": null,
61
+ "add_cross_attention": false,
62
+ "tie_encoder_decoder": false,
63
+ "architectures": [
64
+ "Qwen3ForCausalLM"
65
+ ],
66
+ "finetuning_task": null,
67
+ "id2label": {
68
+ "0": "LABEL_0",
69
+ "1": "LABEL_1"
70
+ },
71
+ "label2id": {
72
+ "LABEL_0": 0,
73
+ "LABEL_1": 1
74
+ },
75
+ "task_specific_params": null,
76
+ "problem_type": null,
77
+ "tokenizer_class": null,
78
+ "prefix": null,
79
+ "bos_token_id": 151643,
80
+ "pad_token_id": 151643,
81
+ "eos_token_id": 151643,
82
+ "sep_token_id": null,
83
+ "decoder_start_token_id": null,
84
+ "max_length": 20,
85
+ "min_length": 0,
86
+ "do_sample": false,
87
+ "early_stopping": false,
88
+ "num_beams": 1,
89
+ "num_beam_groups": 1,
90
+ "diversity_penalty": 0.0,
91
+ "temperature": 1.0,
92
+ "top_k": 50,
93
+ "top_p": 1.0,
94
+ "typical_p": 1.0,
95
+ "repetition_penalty": 1.0,
96
+ "length_penalty": 1.0,
97
+ "no_repeat_ngram_size": 0,
98
+ "encoder_no_repeat_ngram_size": 0,
99
+ "bad_words_ids": null,
100
+ "num_return_sequences": 1,
101
+ "output_scores": false,
102
+ "return_dict_in_generate": false,
103
+ "forced_bos_token_id": null,
104
+ "forced_eos_token_id": null,
105
+ "remove_invalid_values": false,
106
+ "exponential_decay_length_penalty": null,
107
+ "suppress_tokens": null,
108
+ "begin_suppress_tokens": null,
109
+ "_name_or_path": "skymizer/Qwen3-0.6B-Base-GGUF",
110
+ "transformers_version": "4.55.0",
111
+ "model_type": "qwen3",
112
+ "_model_name_or_path": "Qwen3 0.6B Base",
113
+ "tf_legacy_loss": false,
114
+ "use_bfloat16": false,
115
+ "output_attentions": false
116
+ }
hf/qwen3-0.6b-base-q3_k_m/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151643,
5
+ "pad_token_id": 151643,
6
+ "transformers_version": "4.55.0"
7
+ }