3c20756c03fe8a2e9a59ad8169ccc087520b9ec3a7b92e226826af70319b8e5a
Browse files- config.json +66 -0
- generation_config.json +7 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +47 -0
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ai21labs/Jamba-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"JambaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"attn_layer_offset": 4,
|
8 |
+
"attn_layer_period": 8,
|
9 |
+
"auto_map": {
|
10 |
+
"AutoConfig": "ai21labs/Jamba-v0.1--configuration_jamba.JambaConfig",
|
11 |
+
"AutoModel": "ai21labs/Jamba-v0.1--modeling_jamba.JambaModel",
|
12 |
+
"AutoModelForCausalLM": "ai21labs/Jamba-v0.1--modeling_jamba.JambaForCausalLM",
|
13 |
+
"AutoModelForSequenceClassification": "ai21labs/Jamba-v0.1--model.JambaForSequenceClassification"
|
14 |
+
},
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"calc_logits_for_entire_prompt": false,
|
17 |
+
"eos_token_id": 2,
|
18 |
+
"expert_layer_offset": 1,
|
19 |
+
"expert_layer_period": 2,
|
20 |
+
"hidden_act": "silu",
|
21 |
+
"hidden_size": 4096,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 14336,
|
24 |
+
"mamba_conv_bias": true,
|
25 |
+
"mamba_d_conv": 4,
|
26 |
+
"mamba_d_state": 16,
|
27 |
+
"mamba_dt_rank": 256,
|
28 |
+
"mamba_expand": 2,
|
29 |
+
"mamba_inner_layernorms": true,
|
30 |
+
"mamba_proj_bias": false,
|
31 |
+
"model_type": "jamba",
|
32 |
+
"n_ctx": 262144,
|
33 |
+
"num_attention_heads": 32,
|
34 |
+
"num_experts": 16,
|
35 |
+
"num_experts_per_tok": 2,
|
36 |
+
"num_hidden_layers": 32,
|
37 |
+
"num_key_value_heads": 8,
|
38 |
+
"output_router_logits": false,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"quantization_config": {
|
41 |
+
"_load_in_4bit": true,
|
42 |
+
"_load_in_8bit": false,
|
43 |
+
"bnb_4bit_compute_dtype": "float32",
|
44 |
+
"bnb_4bit_quant_storage": "uint8",
|
45 |
+
"bnb_4bit_quant_type": "fp4",
|
46 |
+
"bnb_4bit_use_double_quant": false,
|
47 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
48 |
+
"llm_int8_has_fp16_weight": false,
|
49 |
+
"llm_int8_skip_modules": [
|
50 |
+
"mamba"
|
51 |
+
],
|
52 |
+
"llm_int8_threshold": 6.0,
|
53 |
+
"load_in_4bit": true,
|
54 |
+
"load_in_8bit": false,
|
55 |
+
"quant_method": "bitsandbytes"
|
56 |
+
},
|
57 |
+
"rms_norm_eps": 1e-06,
|
58 |
+
"router_aux_loss_coef": 0.001,
|
59 |
+
"sliding_window": null,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"torch_dtype": "bfloat16",
|
62 |
+
"transformers_version": "4.39.2",
|
63 |
+
"use_cache": true,
|
64 |
+
"use_mamba_kernels": true,
|
65 |
+
"vocab_size": 65536
|
66 |
+
}
|
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": "4.39.2"
|
7 |
+
}
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
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": "<|unk|>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02fd6530b8ede0eedd8e509fcab32da7b1dd04c8119f8498c787100f13112713
|
3 |
+
size 1124742
|
tokenizer_config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<|pad|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<|unk|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<|startoftext|>",
|
39 |
+
"clean_up_tokenization_spaces": false,
|
40 |
+
"eos_token": "<|endoftext|>",
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_token": "<|pad|>",
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"unk_token": "<|unk|>",
|
46 |
+
"use_default_system_prompt": false
|
47 |
+
}
|