Upload 5 files
Browse files- config (1).json +60 -0
- generation_config (1).json +7 -0
- model (1).safetensors +3 -0
- tokenizer (1).json +0 -0
- tokenizer_config (1).json +22 -0
config (1).json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"block_auto_adjust_ff_dim": true,
|
| 6 |
+
"block_dim": 1024,
|
| 7 |
+
"block_ff_dim": 6656,
|
| 8 |
+
"block_ffn_dim_multiplier": 1.0,
|
| 9 |
+
"block_mlp_init_scale": 1.0,
|
| 10 |
+
"block_multiple_of": 256,
|
| 11 |
+
"block_norm_eps": 1e-05,
|
| 12 |
+
"block_out_init_scale": 1.0,
|
| 13 |
+
"block_use_swiglu": true,
|
| 14 |
+
"block_use_xavier_init": true,
|
| 15 |
+
"bos_token_id": 1,
|
| 16 |
+
"conv_L_cache": 3,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": 1024,
|
| 19 |
+
"conv_use_xavier_init": true,
|
| 20 |
+
"dtype": "bfloat16",
|
| 21 |
+
"eos_token_id": 7,
|
| 22 |
+
"hidden_size": 1024,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 6656,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"conv",
|
| 27 |
+
"conv",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"conv",
|
| 30 |
+
"conv",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"conv",
|
| 33 |
+
"conv",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"conv",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"conv",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"conv",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"conv"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 128000,
|
| 44 |
+
"model_type": "lfm2",
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"num_attention_heads": 16,
|
| 47 |
+
"num_heads": 16,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pad_token_id": 0,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"tie_embedding": true,
|
| 56 |
+
"transformers_version": "5.0.0rc1",
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"use_pos_enc": true,
|
| 59 |
+
"vocab_size": 65536
|
| 60 |
+
}
|
generation_config (1).json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 7,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "5.0.0rc1"
|
| 7 |
+
}
|
model (1).safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c9c77a4471a7f590f85240f74ed1fc26df7fbde88c3006724e2f93ca993ea4e
|
| 3 |
+
size 708984464
|
tokenizer (1).json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config (1).json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|startoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"extra_special_tokens": [],
|
| 8 |
+
"is_local": true,
|
| 9 |
+
"legacy": false,
|
| 10 |
+
"model_input_names": [
|
| 11 |
+
"input_ids",
|
| 12 |
+
"attention_mask"
|
| 13 |
+
],
|
| 14 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 15 |
+
"model_specific_special_tokens": {},
|
| 16 |
+
"pad_token": "<|pad|>",
|
| 17 |
+
"sp_model_kwargs": {},
|
| 18 |
+
"spaces_between_special_tokens": false,
|
| 19 |
+
"tokenizer_class": "TokenizersBackend",
|
| 20 |
+
"use_default_system_prompt": false,
|
| 21 |
+
"use_fast": true
|
| 22 |
+
}
|