Upload folder using huggingface_hub
Browse files- config.json +80 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bias_linear": false,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Zamba2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"conv_dimension": 4,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"expansion_factor": 2,
|
| 11 |
+
"ffn_hidden_size": 8192,
|
| 12 |
+
"ft_lora": false,
|
| 13 |
+
"gated_linear_unit": true,
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"kv_channels": 64,
|
| 17 |
+
"layers_block_type": [
|
| 18 |
+
"m",
|
| 19 |
+
"m",
|
| 20 |
+
"m",
|
| 21 |
+
"m",
|
| 22 |
+
"m",
|
| 23 |
+
"g",
|
| 24 |
+
"m",
|
| 25 |
+
"m",
|
| 26 |
+
"m",
|
| 27 |
+
"m",
|
| 28 |
+
"m",
|
| 29 |
+
"g",
|
| 30 |
+
"m",
|
| 31 |
+
"m",
|
| 32 |
+
"m",
|
| 33 |
+
"m",
|
| 34 |
+
"m",
|
| 35 |
+
"g",
|
| 36 |
+
"m",
|
| 37 |
+
"m",
|
| 38 |
+
"m",
|
| 39 |
+
"m",
|
| 40 |
+
"m",
|
| 41 |
+
"g",
|
| 42 |
+
"m",
|
| 43 |
+
"m",
|
| 44 |
+
"m",
|
| 45 |
+
"m",
|
| 46 |
+
"m",
|
| 47 |
+
"g",
|
| 48 |
+
"m",
|
| 49 |
+
"m",
|
| 50 |
+
"m",
|
| 51 |
+
"m",
|
| 52 |
+
"m",
|
| 53 |
+
"g",
|
| 54 |
+
"m",
|
| 55 |
+
"m"
|
| 56 |
+
],
|
| 57 |
+
"lora_rank": 128,
|
| 58 |
+
"mamba_headdim": 64,
|
| 59 |
+
"max_position_embeddings": 4096,
|
| 60 |
+
"model_type": "zamba2",
|
| 61 |
+
"num_attention_heads": 32,
|
| 62 |
+
"num_hidden_layers": 38,
|
| 63 |
+
"num_key_value_heads": 32,
|
| 64 |
+
"num_logits_to_keep": 1,
|
| 65 |
+
"num_mem_blocks": 1,
|
| 66 |
+
"num_query_groups": 32,
|
| 67 |
+
"pad_token_id": 0,
|
| 68 |
+
"rms_norm_eps": 1e-05,
|
| 69 |
+
"rope_theta": 10000,
|
| 70 |
+
"sliding_window": null,
|
| 71 |
+
"state_size": 128,
|
| 72 |
+
"torch_dtype": "bfloat16",
|
| 73 |
+
"transformers_version": "4.43.0.dev0",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"use_mamba_kernels": true,
|
| 76 |
+
"use_mem_rope": true,
|
| 77 |
+
"use_shared_attention_lora": true,
|
| 78 |
+
"use_shared_block_lora": true,
|
| 79 |
+
"vocab_size": 32000
|
| 80 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.43.0.dev0"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11f4b06c2a72440bff4936ddda44707b36b021fe8c593ea80ef5568e45427b8
|
| 3 |
+
size 2430175992
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"additional_special_tokens": [],
|
| 32 |
+
"bos_token": "<s>",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": true,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": null,
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"spaces_between_special_tokens": false,
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|