Update tiny models for FalconMambaForCausalLM
Browse files- config.json +41 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +33 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "silu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"FalconMambaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 11,
|
| 7 |
+
"conv_kernel": 4,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 11,
|
| 10 |
+
"expand": 2,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 32,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 32,
|
| 16 |
+
"is_decoder": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-05,
|
| 18 |
+
"mixer_rms_eps": 1e-06,
|
| 19 |
+
"model_type": "falcon_mamba",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_hidden_layers": 2,
|
| 22 |
+
"pad_token_id": 65024,
|
| 23 |
+
"rescale_prenorm_residual": false,
|
| 24 |
+
"residual_in_fp32": true,
|
| 25 |
+
"state_size": 16,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"time_step_floor": 0.0001,
|
| 28 |
+
"time_step_init_scheme": "random",
|
| 29 |
+
"time_step_max": 0.1,
|
| 30 |
+
"time_step_min": 0.001,
|
| 31 |
+
"time_step_rank": 2,
|
| 32 |
+
"time_step_scale": 1.0,
|
| 33 |
+
"transformers_version": "5.16.0.dev0",
|
| 34 |
+
"type_vocab_size": 16,
|
| 35 |
+
"use_associative_scan": true,
|
| 36 |
+
"use_bias": false,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"use_conv_bias": true,
|
| 39 |
+
"use_mambapy": false,
|
| 40 |
+
"vocab_size": 65025
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 11,
|
| 4 |
+
"eos_token_id": 11,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 65024,
|
| 8 |
+
"transformers_version": "5.16.0.dev0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cca961df82016b8e0cb6ba288686cc33226c0a0241c398f3186a2a19cf0c9e5
|
| 3 |
+
size 16688792
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
">>TITLE<<",
|
| 10 |
+
">>ABSTRACT<<",
|
| 11 |
+
">>INTRODUCTION<<",
|
| 12 |
+
">>SUMMARY<<",
|
| 13 |
+
">>COMMENT<<",
|
| 14 |
+
">>ANSWER<<",
|
| 15 |
+
">>QUESTION<<",
|
| 16 |
+
">>DOMAIN<<",
|
| 17 |
+
">>PREFIX<<",
|
| 18 |
+
">>SUFFIX<<",
|
| 19 |
+
">>MIDDLE<<"
|
| 20 |
+
],
|
| 21 |
+
"is_local": true,
|
| 22 |
+
"local_files_only": false,
|
| 23 |
+
"model_input_names": [
|
| 24 |
+
"input_ids",
|
| 25 |
+
"attention_mask"
|
| 26 |
+
],
|
| 27 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 28 |
+
"pad_token": "<|padding|>",
|
| 29 |
+
"padding_side": "left",
|
| 30 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 31 |
+
"trim_offsets": true,
|
| 32 |
+
"unk_token": "<|endoftext|>"
|
| 33 |
+
}
|