SeanScripts/pixtral-12b-nf4

1{
2  "_name_or_path": "./pixtral-12b",
3  "architectures": [
4    "LlavaForConditionalGeneration"
5  ],
6  "ignore_index": -100,
7  "image_seq_length": 1,
8  "image_token_index": 10,
9  "model_type": "llava",
10  "projector_hidden_act": "gelu",
11  "quantization_config": {
12    "_load_in_4bit": true,
13    "_load_in_8bit": false,
14    "bnb_4bit_compute_dtype": "bfloat16",
15    "bnb_4bit_quant_storage": "uint8",
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,
21    "llm_int8_threshold": 6.0,
22    "load_in_4bit": true,
23    "load_in_8bit": false,
24    "quant_method": "bitsandbytes"
25  },
26  "text_config": {
27    "_name_or_path": "",
28    "add_cross_attention": false,
29    "architectures": null,
30    "attention_dropout": 0.0,
31    "bad_words_ids": null,
32    "begin_suppress_tokens": null,
33    "bos_token_id": 1,
34    "chunk_size_feed_forward": 0,
35    "cross_attention_hidden_size": null,
36    "decoder_start_token_id": null,
37    "diversity_penalty": 0.0,
38    "do_sample": false,
39    "early_stopping": false,
40    "encoder_no_repeat_ngram_size": 0,
41    "eos_token_id": 2,
42    "exponential_decay_length_penalty": null,
43    "finetuning_task": null,
44    "forced_bos_token_id": null,
45    "forced_eos_token_id": null,
46    "head_dim": 128,
47    "hidden_act": "silu",
48    "hidden_size": 5120,
49    "id2label": {
50      "0": "LABEL_0",
51      "1": "LABEL_1"
52    },
53    "initializer_range": 0.02,
54    "intermediate_size": 14336,
55    "is_composition": true,
56    "is_decoder": false,
57    "is_encoder_decoder": false,
58    "label2id": {
59      "LABEL_0": 0,
60      "LABEL_1": 1
61    },
62    "length_penalty": 1.0,
63    "max_length": 20,
64    "max_position_embeddings": 1024000,
65    "min_length": 0,
66    "model_type": "mistral",
67    "no_repeat_ngram_size": 0,
68    "num_attention_heads": 32,
69    "num_beam_groups": 1,
70    "num_beams": 1,
71    "num_hidden_layers": 40,
72    "num_key_value_heads": 8,
73    "num_return_sequences": 1,
74    "output_attentions": false,
75    "output_hidden_states": false,
76    "output_scores": false,
77    "pad_token_id": null,
78    "prefix": null,
79    "problem_type": null,
80    "pruned_heads": {},
81    "remove_invalid_values": false,
82    "repetition_penalty": 1.0,
83    "return_dict": true,
84    "return_dict_in_generate": false,
85    "rms_norm_eps": 1e-05,
86    "rope_theta": 1000000000.0,
87    "sep_token_id": null,
88    "sliding_window": null,
89    "suppress_tokens": null,
90    "task_specific_params": null,
91    "temperature": 1.0,
92    "tf_legacy_loss": false,
93    "tie_encoder_decoder": false,
94    "tie_word_embeddings": false,
95    "tokenizer_class": null,
96    "top_k": 50,
97    "top_p": 1.0,
98    "torch_dtype": null,
99    "torchscript": false,
100    "typical_p": 1.0,
101    "use_bfloat16": false,
102    "use_cache": true,
103    "vocab_size": 131072
104  },
105  "torch_dtype": "float16",
106  "transformers_version": "4.45.0.dev0",
107  "vision_config": {
108    "_name_or_path": "",
109    "add_cross_attention": false,
110    "architectures": null,
111    "attention_dropout": 0.0,
112    "bad_words_ids": null,
113    "begin_suppress_tokens": null,
114    "bos_token_id": null,
115    "chunk_size_feed_forward": 0,
116    "cross_attention_hidden_size": null,
117    "decoder_start_token_id": null,
118    "diversity_penalty": 0.0,
119    "do_sample": false,
120    "early_stopping": false,
121    "encoder_no_repeat_ngram_size": 0,
122    "eos_token_id": null,
123    "exponential_decay_length_penalty": null,
124    "finetuning_task": null,
125    "forced_bos_token_id": null,
126    "forced_eos_token_id": null,
127    "head_dim": 64,
128    "hidden_act": "gelu",
129    "hidden_size": 1024,
130    "id2label": {
131      "0": "LABEL_0",
132      "1": "LABEL_1"
133    },
134    "image_size": 1024,
135    "intermediate_size": 4096,
136    "is_composition": true,
137    "is_decoder": false,
138    "is_encoder_decoder": false,
139    "label2id": {
140      "LABEL_0": 0,
141      "LABEL_1": 1
142    },
143    "length_penalty": 1.0,
144    "max_length": 20,
145    "min_length": 0,
146    "model_type": "pixtral",
147    "no_repeat_ngram_size": 0,
148    "num_attention_heads": 16,
149    "num_beam_groups": 1,
150    "num_beams": 1,
151    "num_channels": 3,
152    "num_hidden_layers": 24,
153    "num_return_sequences": 1,
154    "output_attentions": false,
155    "output_hidden_states": false,
156    "output_scores": false,
157    "pad_token_id": null,
158    "patch_size": 16,
159    "prefix": null,
160    "problem_type": null,
161    "pruned_heads": {},
162    "remove_invalid_values": false,
163    "repetition_penalty": 1.0,
164    "return_dict": true,
165    "return_dict_in_generate": false,
166    "rope_theta": 10000.0,
167    "sep_token_id": null,
168    "suppress_tokens": null,
169    "task_specific_params": null,
170    "temperature": 1.0,
171    "tf_legacy_loss": false,
172    "tie_encoder_decoder": false,
173    "tie_word_embeddings": false,
174    "tokenizer_class": null,
175    "top_k": 50,
176    "top_p": 1.0,
177    "torch_dtype": null,
178    "torchscript": false,
179    "typical_p": 1.0,
180    "use_bfloat16": false
181  },
182  "vision_feature_layer": -1,
183  "vision_feature_select_strategy": "full"
184}
185