Upload folder using huggingface_hub
Browse files- config.json +82 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- tokenizer_config.json +1 -1
config.json
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Mistral3ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"image_token_index": 10,
|
| 7 |
+
"model_type": "mistral3",
|
| 8 |
+
"multimodal_projector_bias": false,
|
| 9 |
+
"projector_hidden_act": "gelu",
|
| 10 |
+
"quantization_config": {
|
| 11 |
+
"_load_in_4bit": true,
|
| 12 |
+
"_load_in_8bit": false,
|
| 13 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 14 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 15 |
+
"bnb_4bit_quant_type": "nf4",
|
| 16 |
+
"bnb_4bit_use_double_quant": true,
|
| 17 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 18 |
+
"llm_int8_has_fp16_weight": false,
|
| 19 |
+
"llm_int8_skip_modules": null,
|
| 20 |
+
"llm_int8_threshold": 6.0,
|
| 21 |
+
"load_in_4bit": true,
|
| 22 |
+
"load_in_8bit": false,
|
| 23 |
+
"quant_method": "bitsandbytes"
|
| 24 |
+
},
|
| 25 |
+
"spatial_merge_size": 2,
|
| 26 |
+
"text_config": {
|
| 27 |
+
"attention_dropout": 0.0,
|
| 28 |
+
"bos_token_id": 1,
|
| 29 |
+
"dtype": "bfloat16",
|
| 30 |
+
"eos_token_id": 2,
|
| 31 |
+
"head_dim": 128,
|
| 32 |
+
"hidden_act": "silu",
|
| 33 |
+
"hidden_size": 4096,
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 14336,
|
| 36 |
+
"max_position_embeddings": 262144,
|
| 37 |
+
"model_type": "ministral3",
|
| 38 |
+
"num_attention_heads": 32,
|
| 39 |
+
"num_hidden_layers": 34,
|
| 40 |
+
"num_key_value_heads": 8,
|
| 41 |
+
"pad_token_id": 11,
|
| 42 |
+
"rms_norm_eps": 1e-05,
|
| 43 |
+
"rope_parameters": {
|
| 44 |
+
"beta_fast": 32.0,
|
| 45 |
+
"beta_slow": 1.0,
|
| 46 |
+
"factor": 16.0,
|
| 47 |
+
"llama_4_scaling_beta": 0.1,
|
| 48 |
+
"mscale": 1.0,
|
| 49 |
+
"mscale_all_dim": 1.0,
|
| 50 |
+
"original_max_position_embeddings": 16384,
|
| 51 |
+
"rope_theta": 1000000.0,
|
| 52 |
+
"rope_type": "yarn",
|
| 53 |
+
"type": "yarn"
|
| 54 |
+
},
|
| 55 |
+
"sliding_window": null,
|
| 56 |
+
"tie_word_embeddings": false,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 131072
|
| 59 |
+
},
|
| 60 |
+
"tie_word_embeddings": false,
|
| 61 |
+
"transformers_version": "5.2.0",
|
| 62 |
+
"vision_config": {
|
| 63 |
+
"attention_dropout": 0.0,
|
| 64 |
+
"dtype": "bfloat16",
|
| 65 |
+
"head_dim": 64,
|
| 66 |
+
"hidden_act": "silu",
|
| 67 |
+
"hidden_size": 1024,
|
| 68 |
+
"image_size": 1540,
|
| 69 |
+
"initializer_range": 0.02,
|
| 70 |
+
"intermediate_size": 4096,
|
| 71 |
+
"model_type": "pixtral",
|
| 72 |
+
"num_attention_heads": 16,
|
| 73 |
+
"num_channels": 3,
|
| 74 |
+
"num_hidden_layers": 24,
|
| 75 |
+
"patch_size": 14,
|
| 76 |
+
"rope_parameters": {
|
| 77 |
+
"rope_theta": 10000.0,
|
| 78 |
+
"rope_type": "default"
|
| 79 |
+
}
|
| 80 |
+
},
|
| 81 |
+
"vision_feature_layer": -1
|
| 82 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 262144,
|
| 5 |
+
"pad_token_id": 11,
|
| 6 |
+
"transformers_version": "5.2.0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63eb9f513881cb5a486edaf8cfbb174cb20c1f34eaaa77dd5af5546e71f146fc
|
| 3 |
+
size 6196366251
|
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
-
"is_local":
|
| 8 |
"legacy": true,
|
| 9 |
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
"pad_token": "<pad>",
|
|
|
|
| 4 |
"bos_token": "<s>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
"legacy": true,
|
| 9 |
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
"pad_token": "<pad>",
|