Hugging Face's logo

mlx-community
/
Llama-OuteTTS-1.0-1B-4bit

Text-to-Speech
MLX
Safetensors
llama
4-bit precision
Model card Files Community
prince-canuma commited on
Commit
e9655c0
·
verified ·
1 Parent(s): 5ea99f6

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. README.md +43 -0
  3. config.json +98 -0
  4. generation_config.json +13 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +379 -0
  7. special_tokens_map.json +0 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ language:
4
+ - en
5
+ - ar
6
+ - zh
7
+ - nl
8
+ - fr
9
+ - de
10
+ - it
11
+ - ja
12
+ - ko
13
+ - lt
14
+ - ru
15
+ - es
16
+ - pt
17
+ - be
18
+ - bn
19
+ - ka
20
+ - hu
21
+ - lv
22
+ - fa
23
+ - pl
24
+ - sw
25
+ - ta
26
+ - uk
27
+ pipeline_tag: text-to-speech
28
+ tags:
29
+ - mlx
30
+ ---
31
+
32
+ # mlx-community/Llama-OuteTTS-1.0-1B-4bit
33
+ This model was converted to MLX format from [`OuteAI/Llama-OuteTTS-1.0-1B`]() using mlx-audio version **0.0.5**.
34
+ Refer to the [original model card](https://huggingface.co/OuteAI/Llama-OuteTTS-1.0-1B) for more details on the model.
35
+ ## Use with mlx
36
+
37
+ ```bash
38
+ pip install -U mlx-audio
39
+ ```
40
+
41
+ ```bash
42
+ python -m mlx_audio.tts.generate --model mlx-community/Llama-OuteTTS-1.0-1B-4bit --max-tokens 100 --temperature 0.0 --text "Describe this image."
43
+ ```
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bad_words_ids": null,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": 133309,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "early_stopping": false,
18
+ "encoder_no_repeat_ngram_size": 0,
19
+ "eos_token_id": 133310,
20
+ "exponential_decay_length_penalty": null,
21
+ "finetuning_task": null,
22
+ "forced_bos_token_id": null,
23
+ "forced_eos_token_id": null,
24
+ "head_dim": 64,
25
+ "hidden_act": "silu",
26
+ "hidden_size": 2048,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 8192,
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "max_position_embeddings": 131072,
42
+ "min_length": 0,
43
+ "mlp_bias": false,
44
+ "model_type": "llama",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_attention_heads": 32,
47
+ "num_beam_groups": 1,
48
+ "num_beams": 1,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "num_return_sequences": 1,
52
+ "output_attentions": false,
53
+ "output_hidden_states": false,
54
+ "output_scores": false,
55
+ "pad_token_id": null,
56
+ "prefix": null,
57
+ "pretraining_tp": 1,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "quantization": {
61
+ "group_size": 64,
62
+ "bits": 4
63
+ },
64
+ "quantization_config": {
65
+ "group_size": 64,
66
+ "bits": 4
67
+ },
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "rms_norm_eps": 1e-05,
73
+ "rope_scaling": {
74
+ "factor": 32.0,
75
+ "high_freq_factor": 4.0,
76
+ "low_freq_factor": 1.0,
77
+ "original_max_position_embeddings": 8192,
78
+ "rope_type": "llama3"
79
+ },
80
+ "rope_theta": 500000.0,
81
+ "sep_token_id": null,
82
+ "suppress_tokens": null,
83
+ "task_specific_params": null,
84
+ "temperature": 1.0,
85
+ "tf_legacy_loss": false,
86
+ "tie_encoder_decoder": false,
87
+ "tie_word_embeddings": true,
88
+ "tokenizer_class": null,
89
+ "top_k": 50,
90
+ "top_p": 1.0,
91
+ "torch_dtype": "bfloat16",
92
+ "torchscript": false,
93
+ "transformers_version": "4.52.0.dev0",
94
+ "typical_p": 1.0,
95
+ "use_bfloat16": false,
96
+ "use_cache": true,
97
+ "vocab_size": 134400
98
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 133309,
4
+ "eos_token_id": 133310,
5
+ "pad_token_id": 128001,
6
+ "transformers_version": "4.48.3",
7
+ "do_sample": true,
8
+ "temperature": 0.4,
9
+ "repetition_penalty": 1.1,
10
+ "top_k": 40,
11
+ "top_p": 0.9,
12
+ "min_p": 0.05
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225077bfa89f01d81c28536aac9846e53bd9384e7eb1463738a5bdcc91b845c2
3
+ size 702361809
model.safetensors.index.json ADDED
@@ -0,0 +1,379 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 702320640
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.biases": "model.safetensors",
7
+ "model.embed_tokens.scales": "model.safetensors",
8
+ "model.embed_tokens.weight": "model.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
10
+ "model.layers.0.mlp.down_proj.biases": "model.safetensors",
11
+ "model.layers.0.mlp.down_proj.scales": "model.safetensors",
12
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
13
+ "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
14
+ "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
16
+ "model.layers.0.mlp.up_proj.biases": "model.safetensors",
17
+ "model.layers.0.mlp.up_proj.scales": "model.safetensors",
18
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
19
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
20
+ "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
21
+ "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
22
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
23
+ "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
24
+ "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
25
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
26
+ "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
27
+ "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
28
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
29
+ "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
30
+ "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
31
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
32
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
33
+ "model.layers.1.mlp.down_proj.biases": "model.safetensors",
34
+ "model.layers.1.mlp.down_proj.scales": "model.safetensors",
35
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
36
+ "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
37
+ "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
38
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
39
+ "model.layers.1.mlp.up_proj.biases": "model.safetensors",
40
+ "model.layers.1.mlp.up_proj.scales": "model.safetensors",
41
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
42
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
43
+ "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
44
+ "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
45
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
46
+ "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
47
+ "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
48
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
49
+ "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
50
+ "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
51
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
52
+ "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
53
+ "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
54
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
55
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
56
+ "model.layers.10.mlp.down_proj.biases": "model.safetensors",
57
+ "model.layers.10.mlp.down_proj.scales": "model.safetensors",
58
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
59
+ "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
60
+ "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
61
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
62
+ "model.layers.10.mlp.up_proj.biases": "model.safetensors",
63
+ "model.layers.10.mlp.up_proj.scales": "model.safetensors",
64
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
65
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
66
+ "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
67
+ "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
68
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
69
+ "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
70
+ "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
71
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
72
+ "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
73
+ "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
74
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
75
+ "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
76
+ "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
77
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
78
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
79
+ "model.layers.11.mlp.down_proj.biases": "model.safetensors",
80
+ "model.layers.11.mlp.down_proj.scales": "model.safetensors",
81
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
82
+ "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
83
+ "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
84
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
85
+ "model.layers.11.mlp.up_proj.biases": "model.safetensors",
86
+ "model.layers.11.mlp.up_proj.scales": "model.safetensors",
87
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
88
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
89
+ "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
90
+ "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
91
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
92
+ "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
93
+ "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
94
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
95
+ "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
96
+ "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
97
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
98
+ "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
99
+ "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
100
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
101
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
102
+ "model.layers.12.mlp.down_proj.biases": "model.safetensors",
103
+ "model.layers.12.mlp.down_proj.scales": "model.safetensors",
104
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
105
+ "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
106
+ "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
107
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
108
+ "model.layers.12.mlp.up_proj.biases": "model.safetensors",
109
+ "model.layers.12.mlp.up_proj.scales": "model.safetensors",
110
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
111
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
112
+ "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
113
+ "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
114
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
115
+ "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
116
+ "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
117
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
118
+ "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
119
+ "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
120
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
121
+ "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
122
+ "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
123
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
124
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
125
+ "model.layers.13.mlp.down_proj.biases": "model.safetensors",
126
+ "model.layers.13.mlp.down_proj.scales": "model.safetensors",
127
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
128
+ "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
129
+ "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
130
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
131
+ "model.layers.13.mlp.up_proj.biases": "model.safetensors",
132
+ "model.layers.13.mlp.up_proj.scales": "model.safetensors",
133
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
134
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
135
+ "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
136
+ "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
137
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
138
+ "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
139
+ "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
140
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
141
+ "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
142
+ "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
143
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
144
+ "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
145
+ "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
146
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
147
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
148
+ "model.layers.14.mlp.down_proj.biases": "model.safetensors",
149
+ "model.layers.14.mlp.down_proj.scales": "model.safetensors",
150
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
151
+ "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
152
+ "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
153
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
154
+ "model.layers.14.mlp.up_proj.biases": "model.safetensors",
155
+ "model.layers.14.mlp.up_proj.scales": "model.safetensors",
156
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
157
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
158
+ "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
159
+ "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
160
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
161
+ "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
162
+ "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
163
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
164
+ "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
165
+ "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
166
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
167
+ "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
168
+ "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
169
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
170
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
171
+ "model.layers.15.mlp.down_proj.biases": "model.safetensors",
172
+ "model.layers.15.mlp.down_proj.scales": "model.safetensors",
173
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
174
+ "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
175
+ "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
176
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
177
+ "model.layers.15.mlp.up_proj.biases": "model.safetensors",
178
+ "model.layers.15.mlp.up_proj.scales": "model.safetensors",
179
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
180
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
181
+ "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
182
+ "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
183
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
184
+ "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
185
+ "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
186
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
187
+ "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
188
+ "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
189
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
190
+ "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
191
+ "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
192
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
193
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
194
+ "model.layers.2.mlp.down_proj.biases": "model.safetensors",
195
+ "model.layers.2.mlp.down_proj.scales": "model.safetensors",
196
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
197
+ "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
198
+ "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
199
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
200
+ "model.layers.2.mlp.up_proj.biases": "model.safetensors",
201
+ "model.layers.2.mlp.up_proj.scales": "model.safetensors",
202
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
203
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
204
+ "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
205
+ "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
206
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
207
+ "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
208
+ "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
209
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
210
+ "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
211
+ "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
212
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
213
+ "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
214
+ "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
215
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
217
+ "model.layers.3.mlp.down_proj.biases": "model.safetensors",
218
+ "model.layers.3.mlp.down_proj.scales": "model.safetensors",
219
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
220
+ "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
221
+ "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
222
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
223
+ "model.layers.3.mlp.up_proj.biases": "model.safetensors",
224
+ "model.layers.3.mlp.up_proj.scales": "model.safetensors",
225
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
226
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
227
+ "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
228
+ "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
229
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
230
+ "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
231
+ "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
232
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
233
+ "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
234
+ "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
235
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
236
+ "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
237
+ "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
238
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
239
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
240
+ "model.layers.4.mlp.down_proj.biases": "model.safetensors",
241
+ "model.layers.4.mlp.down_proj.scales": "model.safetensors",
242
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
243
+ "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
244
+ "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
246
+ "model.layers.4.mlp.up_proj.biases": "model.safetensors",
247
+ "model.layers.4.mlp.up_proj.scales": "model.safetensors",
248
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
249
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
250
+ "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
251
+ "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
252
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
253
+ "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
254
+ "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
255
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
256
+ "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
257
+ "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
258
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
259
+ "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
260
+ "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
261
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
262
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
263
+ "model.layers.5.mlp.down_proj.biases": "model.safetensors",
264
+ "model.layers.5.mlp.down_proj.scales": "model.safetensors",
265
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
266
+ "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
267
+ "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
268
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
269
+ "model.layers.5.mlp.up_proj.biases": "model.safetensors",
270
+ "model.layers.5.mlp.up_proj.scales": "model.safetensors",
271
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
272
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
273
+ "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
274
+ "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
275
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
276
+ "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
277
+ "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
278
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
279
+ "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
280
+ "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
281
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
282
+ "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
283
+ "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
284
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
285
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
286
+ "model.layers.6.mlp.down_proj.biases": "model.safetensors",
287
+ "model.layers.6.mlp.down_proj.scales": "model.safetensors",
288
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
289
+ "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
290
+ "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
291
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
292
+ "model.layers.6.mlp.up_proj.biases": "model.safetensors",
293
+ "model.layers.6.mlp.up_proj.scales": "model.safetensors",
294
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
295
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
296
+ "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
297
+ "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
298
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
299
+ "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
300
+ "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
301
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
302
+ "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
303
+ "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
304
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
305
+ "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
306
+ "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
309
+ "model.layers.7.mlp.down_proj.biases": "model.safetensors",
310
+ "model.layers.7.mlp.down_proj.scales": "model.safetensors",
311
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
312
+ "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
313
+ "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
314
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
315
+ "model.layers.7.mlp.up_proj.biases": "model.safetensors",
316
+ "model.layers.7.mlp.up_proj.scales": "model.safetensors",
317
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
318
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
319
+ "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
320
+ "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
321
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
322
+ "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
323
+ "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
324
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
325
+ "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
326
+ "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
327
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
328
+ "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
329
+ "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
330
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
331
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
332
+ "model.layers.8.mlp.down_proj.biases": "model.safetensors",
333
+ "model.layers.8.mlp.down_proj.scales": "model.safetensors",
334
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
335
+ "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
336
+ "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
337
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
338
+ "model.layers.8.mlp.up_proj.biases": "model.safetensors",
339
+ "model.layers.8.mlp.up_proj.scales": "model.safetensors",
340
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
341
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
342
+ "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
343
+ "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
344
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
345
+ "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
346
+ "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
347
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
348
+ "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
349
+ "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
350
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
351
+ "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
352
+ "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
353
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
354
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
355
+ "model.layers.9.mlp.down_proj.biases": "model.safetensors",
356
+ "model.layers.9.mlp.down_proj.scales": "model.safetensors",
357
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
358
+ "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
359
+ "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
360
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
361
+ "model.layers.9.mlp.up_proj.biases": "model.safetensors",
362
+ "model.layers.9.mlp.up_proj.scales": "model.safetensors",
363
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
364
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
365
+ "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
366
+ "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
367
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
368
+ "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
369
+ "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
370
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
371
+ "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
372
+ "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
373
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
374
+ "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
375
+ "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
376
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
377
+ "model.norm.weight": "model.safetensors"
378
+ }
379
+ }
special_tokens_map.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec54a55e3c6fc7318ea02cbd1a6eb1fb180bff1b58acbf068504a25f1b407b7b
3
+ size 18366636
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff