autogptq format
Browse filesSigned-off-by: wenhuach <[email protected]>
- config.json +95 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +68 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +192 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/models/OLMo-2-1124-13B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Olmo2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"eos_token_id": 100257,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 13824,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "olmo2",
|
| 15 |
+
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 40,
|
| 17 |
+
"num_key_value_heads": 40,
|
| 18 |
+
"pad_token_id": 100277,
|
| 19 |
+
"quantization_config": {
|
| 20 |
+
"amp": true,
|
| 21 |
+
"autoround_version": "0.4.2.dev",
|
| 22 |
+
"batch_size": 8,
|
| 23 |
+
"bits": 4,
|
| 24 |
+
"damp_percent": 0.01,
|
| 25 |
+
"data_type": "int",
|
| 26 |
+
"desc_act": false,
|
| 27 |
+
"enable_minmax_tuning": true,
|
| 28 |
+
"enable_norm_bias_tuning": false,
|
| 29 |
+
"enable_quanted_input": true,
|
| 30 |
+
"gradient_accumulate_steps": 1,
|
| 31 |
+
"group_size": 128,
|
| 32 |
+
"iters": 1000,
|
| 33 |
+
"low_gpu_mem_usage": false,
|
| 34 |
+
"lr": 0.001,
|
| 35 |
+
"minmax_lr": 0.001,
|
| 36 |
+
"nsamples": 512,
|
| 37 |
+
"quant_method": "gptq",
|
| 38 |
+
"scale_dtype": "torch.float16",
|
| 39 |
+
"seqlen": 2048,
|
| 40 |
+
"sym": true,
|
| 41 |
+
"to_quant_block_names": [
|
| 42 |
+
[
|
| 43 |
+
"model.layers.0",
|
| 44 |
+
"model.layers.1",
|
| 45 |
+
"model.layers.2",
|
| 46 |
+
"model.layers.3",
|
| 47 |
+
"model.layers.4",
|
| 48 |
+
"model.layers.5",
|
| 49 |
+
"model.layers.6",
|
| 50 |
+
"model.layers.7",
|
| 51 |
+
"model.layers.8",
|
| 52 |
+
"model.layers.9",
|
| 53 |
+
"model.layers.10",
|
| 54 |
+
"model.layers.11",
|
| 55 |
+
"model.layers.12",
|
| 56 |
+
"model.layers.13",
|
| 57 |
+
"model.layers.14",
|
| 58 |
+
"model.layers.15",
|
| 59 |
+
"model.layers.16",
|
| 60 |
+
"model.layers.17",
|
| 61 |
+
"model.layers.18",
|
| 62 |
+
"model.layers.19",
|
| 63 |
+
"model.layers.20",
|
| 64 |
+
"model.layers.21",
|
| 65 |
+
"model.layers.22",
|
| 66 |
+
"model.layers.23",
|
| 67 |
+
"model.layers.24",
|
| 68 |
+
"model.layers.25",
|
| 69 |
+
"model.layers.26",
|
| 70 |
+
"model.layers.27",
|
| 71 |
+
"model.layers.28",
|
| 72 |
+
"model.layers.29",
|
| 73 |
+
"model.layers.30",
|
| 74 |
+
"model.layers.31",
|
| 75 |
+
"model.layers.32",
|
| 76 |
+
"model.layers.33",
|
| 77 |
+
"model.layers.34",
|
| 78 |
+
"model.layers.35",
|
| 79 |
+
"model.layers.36",
|
| 80 |
+
"model.layers.37",
|
| 81 |
+
"model.layers.38",
|
| 82 |
+
"model.layers.39"
|
| 83 |
+
]
|
| 84 |
+
],
|
| 85 |
+
"true_sequential": false
|
| 86 |
+
},
|
| 87 |
+
"rms_norm_eps": 1e-06,
|
| 88 |
+
"rope_scaling": null,
|
| 89 |
+
"rope_theta": 500000,
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"torch_dtype": "float16",
|
| 92 |
+
"transformers_version": "4.47.0.dev0",
|
| 93 |
+
"use_cache": false,
|
| 94 |
+
"vocab_size": 100352
|
| 95 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 100257,
|
| 4 |
+
"pad_token_id": 100277,
|
| 5 |
+
"transformers_version": "4.47.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:963e3d654a0c3dddeb3ac2a3bf697202c232f8b1e80e26259259875d5febf88d
|
| 3 |
+
size 4990540208
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe16cb5d8de1ad21a3674062320dea5d68c93cacc040e033fee1c7e37947bbb4
|
| 3 |
+
size 3669572160
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
quantize_config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bits": 4,
|
| 3 |
+
"group_size": 128,
|
| 4 |
+
"sym": true,
|
| 5 |
+
"data_type": "int",
|
| 6 |
+
"enable_quanted_input": true,
|
| 7 |
+
"enable_minmax_tuning": true,
|
| 8 |
+
"seqlen": 2048,
|
| 9 |
+
"batch_size": 8,
|
| 10 |
+
"scale_dtype": "torch.float16",
|
| 11 |
+
"lr": 0.001,
|
| 12 |
+
"minmax_lr": 0.001,
|
| 13 |
+
"gradient_accumulate_steps": 1,
|
| 14 |
+
"iters": 1000,
|
| 15 |
+
"amp": true,
|
| 16 |
+
"nsamples": 512,
|
| 17 |
+
"low_gpu_mem_usage": false,
|
| 18 |
+
"to_quant_block_names": [
|
| 19 |
+
[
|
| 20 |
+
"model.layers.0",
|
| 21 |
+
"model.layers.1",
|
| 22 |
+
"model.layers.2",
|
| 23 |
+
"model.layers.3",
|
| 24 |
+
"model.layers.4",
|
| 25 |
+
"model.layers.5",
|
| 26 |
+
"model.layers.6",
|
| 27 |
+
"model.layers.7",
|
| 28 |
+
"model.layers.8",
|
| 29 |
+
"model.layers.9",
|
| 30 |
+
"model.layers.10",
|
| 31 |
+
"model.layers.11",
|
| 32 |
+
"model.layers.12",
|
| 33 |
+
"model.layers.13",
|
| 34 |
+
"model.layers.14",
|
| 35 |
+
"model.layers.15",
|
| 36 |
+
"model.layers.16",
|
| 37 |
+
"model.layers.17",
|
| 38 |
+
"model.layers.18",
|
| 39 |
+
"model.layers.19",
|
| 40 |
+
"model.layers.20",
|
| 41 |
+
"model.layers.21",
|
| 42 |
+
"model.layers.22",
|
| 43 |
+
"model.layers.23",
|
| 44 |
+
"model.layers.24",
|
| 45 |
+
"model.layers.25",
|
| 46 |
+
"model.layers.26",
|
| 47 |
+
"model.layers.27",
|
| 48 |
+
"model.layers.28",
|
| 49 |
+
"model.layers.29",
|
| 50 |
+
"model.layers.30",
|
| 51 |
+
"model.layers.31",
|
| 52 |
+
"model.layers.32",
|
| 53 |
+
"model.layers.33",
|
| 54 |
+
"model.layers.34",
|
| 55 |
+
"model.layers.35",
|
| 56 |
+
"model.layers.36",
|
| 57 |
+
"model.layers.37",
|
| 58 |
+
"model.layers.38",
|
| 59 |
+
"model.layers.39"
|
| 60 |
+
]
|
| 61 |
+
],
|
| 62 |
+
"enable_norm_bias_tuning": false,
|
| 63 |
+
"autoround_version": "0.4.2.dev",
|
| 64 |
+
"quant_method": "gptq",
|
| 65 |
+
"desc_act": false,
|
| 66 |
+
"true_sequential": false,
|
| 67 |
+
"damp_percent": 0.01
|
| 68 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"100256": {
|
| 6 |
+
"content": "<|extra_id_0|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": false
|
| 12 |
+
},
|
| 13 |
+
"100257": {
|
| 14 |
+
"content": "<|endoftext|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"100258": {
|
| 22 |
+
"content": "<|fim_prefix|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"100259": {
|
| 30 |
+
"content": "<|fim_middle|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"100260": {
|
| 38 |
+
"content": "<|fim_suffix|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"100261": {
|
| 46 |
+
"content": "|||PHONE_NUMBER|||",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"100262": {
|
| 54 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"100263": {
|
| 62 |
+
"content": "|||IP_ADDRESS|||",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"100264": {
|
| 70 |
+
"content": "<|im_start|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"100265": {
|
| 78 |
+
"content": "<|im_end|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"100266": {
|
| 86 |
+
"content": "<|extra_id_1|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"100267": {
|
| 94 |
+
"content": "<|extra_id_2|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"100268": {
|
| 102 |
+
"content": "<|extra_id_3|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"100269": {
|
| 110 |
+
"content": "<|extra_id_4|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"100270": {
|
| 118 |
+
"content": "<|extra_id_5|>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"100271": {
|
| 126 |
+
"content": "<|extra_id_6|>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"100272": {
|
| 134 |
+
"content": "<|extra_id_7|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"100273": {
|
| 142 |
+
"content": "<|extra_id_8|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"100274": {
|
| 150 |
+
"content": "<|extra_id_9|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"100275": {
|
| 158 |
+
"content": "<|extra_id_10|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"100276": {
|
| 166 |
+
"content": "<|endofprompt|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": true
|
| 172 |
+
},
|
| 173 |
+
"100277": {
|
| 174 |
+
"content": "<|pad|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": true
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"bos_token": "<|endoftext|>",
|
| 183 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<|endoftext|>",
|
| 186 |
+
"errors": "replace",
|
| 187 |
+
"extra_special_tokens": {},
|
| 188 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 189 |
+
"pad_token": "<|pad|>",
|
| 190 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 191 |
+
"unk_token": "<|endoftext|>"
|
| 192 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|