Add files using upload-large-folder tool
Browse files- config.json +14 -13
- generation_config.json +3 -2
- model.safetensors.index.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -4,7 +4,6 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
|
@@ -17,23 +16,25 @@
|
|
| 17 |
"num_attention_heads": 64,
|
| 18 |
"num_hidden_layers": 64,
|
| 19 |
"num_key_value_heads": 8,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"rms_norm_eps": 1e-06,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 1000000,
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
-
"transformers_version": "4.
|
|
|
|
| 27 |
"use_cache": true,
|
| 28 |
"use_sliding_window": false,
|
| 29 |
-
"vocab_size": 151936
|
| 30 |
-
|
| 31 |
-
"activation_scheme": "dynamic",
|
| 32 |
-
"fmt": "e4m3",
|
| 33 |
-
"quant_method": "fp8",
|
| 34 |
-
"weight_block_size": [
|
| 35 |
-
128,
|
| 36 |
-
128
|
| 37 |
-
]
|
| 38 |
-
}
|
| 39 |
-
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"eos_token_id": 151645,
|
| 8 |
"head_dim": 128,
|
| 9 |
"hidden_act": "silu",
|
|
|
|
| 16 |
"num_attention_heads": 64,
|
| 17 |
"num_hidden_layers": 64,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 151654,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"activation_scheme": "dynamic",
|
| 22 |
+
"modules_to_not_convert": null,
|
| 23 |
+
"quant_method": "fp8",
|
| 24 |
+
"weight_block_size": [
|
| 25 |
+
128,
|
| 26 |
+
128
|
| 27 |
+
]
|
| 28 |
+
},
|
| 29 |
"rms_norm_eps": 1e-06,
|
| 30 |
"rope_scaling": null,
|
| 31 |
"rope_theta": 1000000,
|
| 32 |
"sliding_window": null,
|
| 33 |
"tie_word_embeddings": false,
|
| 34 |
"torch_dtype": "bfloat16",
|
| 35 |
+
"transformers_version": "4.52.0.dev0",
|
| 36 |
+
"unsloth_fixed": true,
|
| 37 |
"use_cache": true,
|
| 38 |
"use_sliding_window": false,
|
| 39 |
+
"vocab_size": 151936
|
| 40 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
generation_config.json
CHANGED
|
@@ -5,9 +5,10 @@
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
-
"
|
|
|
|
| 9 |
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "4.
|
| 13 |
}
|
|
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
+
"max_length": 40960,
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
"temperature": 0.6,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.95,
|
| 13 |
+
"transformers_version": "4.52.0.dev0"
|
| 14 |
}
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00007-of-00007.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 34322434048
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00007-of-00007.safetensors",
|
tokenizer_config.json
CHANGED
|
@@ -231,7 +231,7 @@
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
-
"model_max_length":
|
| 235 |
"pad_token": "<|vision_pad|>",
|
| 236 |
"padding_side": "left",
|
| 237 |
"split_special_tokens": false,
|
|
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 40960,
|
| 235 |
"pad_token": "<|vision_pad|>",
|
| 236 |
"padding_side": "left",
|
| 237 |
"split_special_tokens": false,
|