Hugging Face's logo

onnx-community
/
Pleias-1.2b-Preview

Text Generation
Transformers.js
ONNX
llama
Model card Files Community
Xenova HF staff commited on
Commit
b305734
·
verified ·
1 Parent(s): a9fffde

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +2 -0
  2. config.json +36 -0
  3. generation_config.json +6 -0
  4. onnx/model.onnx +3 -0
  5. onnx/model.onnx_data +3 -0
  6. onnx/model_bnb4.onnx +3 -0
  7. onnx/model_fp16.onnx +3 -0
  8. onnx/model_fp16.onnx_data +3 -0
  9. onnx/model_int8.onnx +3 -0
  10. onnx/model_q4.onnx +3 -0
  11. onnx/model_q4f16.onnx +3 -0
  12. onnx/model_quantized.onnx +3 -0
  13. onnx/model_uint8.onnx +3 -0
  14. special_tokens_map.json +1 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +39 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PleIAs/Pleias-1.2b-Preview",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 6144,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 22,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000,
25
+ "tie_word_embeddings": true,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.46.3",
28
+ "use_cache": true,
29
+ "vocab_size": 65536,
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "q4f16": "float16",
33
+ "fp16": "float16"
34
+ }
35
+ }
36
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.46.3"
6
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce645fc067a11b62e305f724e573160e866b99b3d243326371e17aa9bb7e1c3e
3
+ size 114000
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737e270be5c1796d3384508ac8de6df15398184851e3b87be7bf8296d5d3fa04
3
+ size 4782399488
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6805efeda8e325eea6e3e7cff3d061eb03a147492be82c72cb57735ba618efa
3
+ size 1134792521
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375f99999e540fd63f8697a611657d90e16f0b31f20142a19dd91e8490036bfb
3
+ size 114881
onnx/model_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b744e5d2b72eae2847b208e9929bc2c2b0b6cefe0a0cab2817dfc9f9a261a7e8
3
+ size 2391199744
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fd8aedc3608b896b8e5fd308c46f194eec6b3ae2a2bd8d8237d59147b67af2
3
+ size 1196508911
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f188e5cfa7aa6641e62e3dbeaed0a689eee6395c54a7f6a2785c54c55a4074a
3
+ size 1201113985
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e19a031326580768870ba64cee1550f56e89d850f7e930ee876239a63a4ab35
3
+ size 865909678
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e24d620cde7a299ee5af0ee8d0e8c75d0ac05d80dcee7070672380a0c55f27
3
+ size 1196508969
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e24d620cde7a299ee5af0ee8d0e8c75d0ac05d80dcee7070672380a0c55f27
3
+ size 1196508969
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|end_of_text|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": true,
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "tokenizer_class": "PreTrainedTokenizerFast"
39
+ }