Upload 8 files
Browse files- .gitattributes +1 -0
- config.json +129 -3
- generation_config.json +1 -1
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +0 -0
- tokenizer.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
|
config.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"bnb_4bit_compute_dtype": "bfloat16",
|
15 |
"bnb_4bit_quant_storage": "bfloat16",
|
16 |
"bnb_4bit_quant_type": "nf4",
|
17 |
-
"bnb_4bit_use_double_quant":
|
18 |
"llm_int8_enable_fp32_cpu_offload": false,
|
19 |
"llm_int8_has_fp16_weight": false,
|
20 |
"llm_int8_skip_modules": null,
|
@@ -24,21 +24,73 @@
|
|
24 |
"quant_method": "bitsandbytes"
|
25 |
},
|
26 |
"text_config": {
|
|
|
27 |
"_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
|
|
28 |
"architectures": [
|
29 |
"LlamaForCausalLM"
|
30 |
],
|
|
|
|
|
|
|
|
|
31 |
"bos_token_id": 128000,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"eos_token_id": [
|
33 |
128001,
|
34 |
128008,
|
35 |
128009
|
36 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
"intermediate_size": 14336,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
"max_position_embeddings": 131072,
|
|
|
|
|
39 |
"model_type": "llama",
|
|
|
|
|
|
|
|
|
|
|
40 |
"num_key_value_heads": 8,
|
|
|
|
|
|
|
|
|
41 |
"pad_token_id": 128004,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
"rms_norm_eps": 1e-05,
|
43 |
"rope_scaling": {
|
44 |
"factor": 8.0,
|
@@ -48,27 +100,101 @@
|
|
48 |
"rope_type": "llama3"
|
49 |
},
|
50 |
"rope_theta": 500000.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"torch_dtype": "bfloat16",
|
|
|
|
|
52 |
"unsloth_version": "2024.9",
|
|
|
|
|
53 |
"vocab_size": 128256
|
54 |
},
|
55 |
"torch_dtype": "bfloat16",
|
56 |
-
"transformers_version": "4.
|
57 |
"vision_config": {
|
|
|
58 |
"_name_or_path": "google/siglip-so400m-patch14-384",
|
|
|
59 |
"architectures": [
|
60 |
"SiglipVisionModel"
|
61 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
"hidden_act": "gelu_pytorch_tanh",
|
63 |
"hidden_size": 1152,
|
|
|
|
|
|
|
|
|
64 |
"image_size": 384,
|
65 |
"intermediate_size": 4304,
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
"layer_norm_eps": 1e-06,
|
|
|
|
|
|
|
67 |
"model_type": "siglip_vision_model",
|
|
|
68 |
"num_attention_heads": 16,
|
|
|
|
|
|
|
69 |
"num_hidden_layers": 27,
|
|
|
|
|
|
|
|
|
|
|
70 |
"patch_size": 14,
|
71 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
},
|
73 |
"vision_feature_layer": -2,
|
74 |
"vision_feature_select_strategy": "full"
|
|
|
14 |
"bnb_4bit_compute_dtype": "bfloat16",
|
15 |
"bnb_4bit_quant_storage": "bfloat16",
|
16 |
"bnb_4bit_quant_type": "nf4",
|
17 |
+
"bnb_4bit_use_double_quant": false,
|
18 |
"llm_int8_enable_fp32_cpu_offload": false,
|
19 |
"llm_int8_has_fp16_weight": false,
|
20 |
"llm_int8_skip_modules": null,
|
|
|
24 |
"quant_method": "bitsandbytes"
|
25 |
},
|
26 |
"text_config": {
|
27 |
+
"_attn_implementation_autoset": false,
|
28 |
"_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct",
|
29 |
+
"add_cross_attention": false,
|
30 |
"architectures": [
|
31 |
"LlamaForCausalLM"
|
32 |
],
|
33 |
+
"attention_bias": false,
|
34 |
+
"attention_dropout": 0.0,
|
35 |
+
"bad_words_ids": null,
|
36 |
+
"begin_suppress_tokens": null,
|
37 |
"bos_token_id": 128000,
|
38 |
+
"chunk_size_feed_forward": 0,
|
39 |
+
"cross_attention_hidden_size": null,
|
40 |
+
"decoder_start_token_id": null,
|
41 |
+
"diversity_penalty": 0.0,
|
42 |
+
"do_sample": false,
|
43 |
+
"early_stopping": false,
|
44 |
+
"encoder_no_repeat_ngram_size": 0,
|
45 |
"eos_token_id": [
|
46 |
128001,
|
47 |
128008,
|
48 |
128009
|
49 |
],
|
50 |
+
"exponential_decay_length_penalty": null,
|
51 |
+
"finetuning_task": null,
|
52 |
+
"forced_bos_token_id": null,
|
53 |
+
"forced_eos_token_id": null,
|
54 |
+
"head_dim": 128,
|
55 |
+
"hidden_act": "silu",
|
56 |
+
"hidden_size": 4096,
|
57 |
+
"id2label": {
|
58 |
+
"0": "LABEL_0",
|
59 |
+
"1": "LABEL_1"
|
60 |
+
},
|
61 |
+
"initializer_range": 0.02,
|
62 |
"intermediate_size": 14336,
|
63 |
+
"is_decoder": false,
|
64 |
+
"is_encoder_decoder": false,
|
65 |
+
"label2id": {
|
66 |
+
"LABEL_0": 0,
|
67 |
+
"LABEL_1": 1
|
68 |
+
},
|
69 |
+
"length_penalty": 1.0,
|
70 |
+
"max_length": 20,
|
71 |
"max_position_embeddings": 131072,
|
72 |
+
"min_length": 0,
|
73 |
+
"mlp_bias": false,
|
74 |
"model_type": "llama",
|
75 |
+
"no_repeat_ngram_size": 0,
|
76 |
+
"num_attention_heads": 32,
|
77 |
+
"num_beam_groups": 1,
|
78 |
+
"num_beams": 1,
|
79 |
+
"num_hidden_layers": 32,
|
80 |
"num_key_value_heads": 8,
|
81 |
+
"num_return_sequences": 1,
|
82 |
+
"output_attentions": false,
|
83 |
+
"output_hidden_states": false,
|
84 |
+
"output_scores": false,
|
85 |
"pad_token_id": 128004,
|
86 |
+
"prefix": null,
|
87 |
+
"pretraining_tp": 1,
|
88 |
+
"problem_type": null,
|
89 |
+
"pruned_heads": {},
|
90 |
+
"remove_invalid_values": false,
|
91 |
+
"repetition_penalty": 1.0,
|
92 |
+
"return_dict": true,
|
93 |
+
"return_dict_in_generate": false,
|
94 |
"rms_norm_eps": 1e-05,
|
95 |
"rope_scaling": {
|
96 |
"factor": 8.0,
|
|
|
100 |
"rope_type": "llama3"
|
101 |
},
|
102 |
"rope_theta": 500000.0,
|
103 |
+
"sep_token_id": null,
|
104 |
+
"suppress_tokens": null,
|
105 |
+
"task_specific_params": null,
|
106 |
+
"temperature": 1.0,
|
107 |
+
"tf_legacy_loss": false,
|
108 |
+
"tie_encoder_decoder": false,
|
109 |
+
"tie_word_embeddings": false,
|
110 |
+
"tokenizer_class": null,
|
111 |
+
"top_k": 50,
|
112 |
+
"top_p": 1.0,
|
113 |
"torch_dtype": "bfloat16",
|
114 |
+
"torchscript": false,
|
115 |
+
"typical_p": 1.0,
|
116 |
"unsloth_version": "2024.9",
|
117 |
+
"use_bfloat16": false,
|
118 |
+
"use_cache": true,
|
119 |
"vocab_size": 128256
|
120 |
},
|
121 |
"torch_dtype": "bfloat16",
|
122 |
+
"transformers_version": "4.46.1",
|
123 |
"vision_config": {
|
124 |
+
"_attn_implementation_autoset": false,
|
125 |
"_name_or_path": "google/siglip-so400m-patch14-384",
|
126 |
+
"add_cross_attention": false,
|
127 |
"architectures": [
|
128 |
"SiglipVisionModel"
|
129 |
],
|
130 |
+
"attention_dropout": 0.0,
|
131 |
+
"bad_words_ids": null,
|
132 |
+
"begin_suppress_tokens": null,
|
133 |
+
"bos_token_id": null,
|
134 |
+
"chunk_size_feed_forward": 0,
|
135 |
+
"cross_attention_hidden_size": null,
|
136 |
+
"decoder_start_token_id": null,
|
137 |
+
"diversity_penalty": 0.0,
|
138 |
+
"do_sample": false,
|
139 |
+
"early_stopping": false,
|
140 |
+
"encoder_no_repeat_ngram_size": 0,
|
141 |
+
"eos_token_id": null,
|
142 |
+
"exponential_decay_length_penalty": null,
|
143 |
+
"finetuning_task": null,
|
144 |
+
"forced_bos_token_id": null,
|
145 |
+
"forced_eos_token_id": null,
|
146 |
"hidden_act": "gelu_pytorch_tanh",
|
147 |
"hidden_size": 1152,
|
148 |
+
"id2label": {
|
149 |
+
"0": "LABEL_0",
|
150 |
+
"1": "LABEL_1"
|
151 |
+
},
|
152 |
"image_size": 384,
|
153 |
"intermediate_size": 4304,
|
154 |
+
"is_decoder": false,
|
155 |
+
"is_encoder_decoder": false,
|
156 |
+
"label2id": {
|
157 |
+
"LABEL_0": 0,
|
158 |
+
"LABEL_1": 1
|
159 |
+
},
|
160 |
"layer_norm_eps": 1e-06,
|
161 |
+
"length_penalty": 1.0,
|
162 |
+
"max_length": 20,
|
163 |
+
"min_length": 0,
|
164 |
"model_type": "siglip_vision_model",
|
165 |
+
"no_repeat_ngram_size": 0,
|
166 |
"num_attention_heads": 16,
|
167 |
+
"num_beam_groups": 1,
|
168 |
+
"num_beams": 1,
|
169 |
+
"num_channels": 3,
|
170 |
"num_hidden_layers": 27,
|
171 |
+
"num_return_sequences": 1,
|
172 |
+
"output_attentions": false,
|
173 |
+
"output_hidden_states": false,
|
174 |
+
"output_scores": false,
|
175 |
+
"pad_token_id": null,
|
176 |
"patch_size": 14,
|
177 |
+
"prefix": null,
|
178 |
+
"problem_type": null,
|
179 |
+
"pruned_heads": {},
|
180 |
+
"remove_invalid_values": false,
|
181 |
+
"repetition_penalty": 1.0,
|
182 |
+
"return_dict": true,
|
183 |
+
"return_dict_in_generate": false,
|
184 |
+
"sep_token_id": null,
|
185 |
+
"suppress_tokens": null,
|
186 |
+
"task_specific_params": null,
|
187 |
+
"temperature": 1.0,
|
188 |
+
"tf_legacy_loss": false,
|
189 |
+
"tie_encoder_decoder": false,
|
190 |
+
"tie_word_embeddings": true,
|
191 |
+
"tokenizer_class": null,
|
192 |
+
"top_k": 50,
|
193 |
+
"top_p": 1.0,
|
194 |
+
"torch_dtype": "float32",
|
195 |
+
"torchscript": false,
|
196 |
+
"typical_p": 1.0,
|
197 |
+
"use_bfloat16": false
|
198 |
},
|
199 |
"vision_feature_layer": -2,
|
200 |
"vision_feature_select_strategy": "full"
|
generation_config.json
CHANGED
@@ -7,5 +7,5 @@
|
|
7 |
128009
|
8 |
],
|
9 |
"pad_token_id": 128004,
|
10 |
-
"transformers_version": "4.
|
11 |
}
|
|
|
7 |
128009
|
8 |
],
|
9 |
"pad_token_id": 128004,
|
10 |
+
"transformers_version": "4.46.1"
|
11 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f221faf3397922833bdd83a8b013a3a18b76cb55833e75d612816787bf0b6d83
|
3 |
+
size 4995370826
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c26a255302a083252f57e1cb03f01641e3378a1dd84e015c5fbc14a46507b93
|
3 |
+
size 1296091330
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|