erfanvaredi
commited on
Commit
•
6c6b597
1
Parent(s):
5b97e52
Upload folder using huggingface_hub
Browse files- config.json +54 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -0
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "core42/jais-13b-chat",
|
3 |
+
"activation_function": "swiglu",
|
4 |
+
"architectures": [
|
5 |
+
"JAISLMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "core42/jais-13b-chat--configuration_jais.JAISConfig",
|
10 |
+
"AutoModel": "core42/jais-13b-chat--modeling_jais.JAISModel",
|
11 |
+
"AutoModelForCausalLM": "core42/jais-13b-chat--modeling_jais.JAISLMHeadModel",
|
12 |
+
"AutoModelForQuestionAnswering": "core42/jais-13b-chat--modeling_jais.JAISForQuestionAnswering",
|
13 |
+
"AutoModelForSequenceClassification": "core42/jais-13b-chat--modeling_jais.JAISForSequenceClassification",
|
14 |
+
"AutoModelForTokenClassification": "core42/jais-13b-chat--modeling_jais.JAISForTokenClassification"
|
15 |
+
},
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"embd_pdrop": 0.0,
|
18 |
+
"embeddings_scale": 14.6,
|
19 |
+
"eos_token_id": 0,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"layer_norm_epsilon": 1e-05,
|
22 |
+
"model_type": "jais",
|
23 |
+
"n_embd": 5120,
|
24 |
+
"n_head": 40,
|
25 |
+
"n_inner": 13653,
|
26 |
+
"n_layer": 40,
|
27 |
+
"n_positions": 2048,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "alibi",
|
30 |
+
"quantization_config": {
|
31 |
+
"_load_in_4bit": true,
|
32 |
+
"_load_in_8bit": false,
|
33 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
34 |
+
"bnb_4bit_quant_type": "nf4",
|
35 |
+
"bnb_4bit_use_double_quant": true,
|
36 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
37 |
+
"llm_int8_has_fp16_weight": false,
|
38 |
+
"llm_int8_skip_modules": null,
|
39 |
+
"llm_int8_threshold": 6.0,
|
40 |
+
"load_in_4bit": true,
|
41 |
+
"load_in_8bit": false,
|
42 |
+
"quant_method": "bitsandbytes"
|
43 |
+
},
|
44 |
+
"reorder_and_upcast_attn": false,
|
45 |
+
"resid_pdrop": 0.0,
|
46 |
+
"scale_attn_by_inverse_layer_idx": false,
|
47 |
+
"scale_attn_weights": true,
|
48 |
+
"scale_qk_dot_by_d": true,
|
49 |
+
"torch_dtype": "float16",
|
50 |
+
"transformers_version": "4.38.0.dev0",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 84992,
|
53 |
+
"width_scale": 0.11100000000000002
|
54 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.38.0.dev0"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a65967c633ee1d704d3eb3c5f7fee35311e69780ce35203887d7a216c81a327
|
3 |
+
size 4985327161
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0acf99082b74a2aa00a8b0f19b8daa6d3b921cfaa10f114cad9a7e2dde86a37d
|
3 |
+
size 2382339361
|
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": "<|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": "<|endoftext|>",
|
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 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<|endoftext|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
}
|
11 |
+
},
|
12 |
+
"bos_token": "<|endoftext|>",
|
13 |
+
"clean_up_tokenization_spaces": true,
|
14 |
+
"eos_token": "<|endoftext|>",
|
15 |
+
"model_max_length": 2048,
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
18 |
+
"unk_token": "<|endoftext|>"
|
19 |
+
}
|