Upload optimized ONNX model (#1)
Browse files- Upload optimized ONNX model (b69a4e7576e006f8b5af0fa15e8187c84f21af86)
- Delete onnx/model_bnb4.onnx (8940cfffaba4dfd3e4022f5a180467da2ae7bc76)
- Delete onnx/model_int8.onnx (5ff91e5ccacb0daddd929c849474b4a903bc6412)
- Delete onnx/model_uint8.onnx (917277aa018cd670cc7d40ef37a3c7ba62d74875)
- .gitattributes +5 -0
- config.json +21 -7
- generation_config.json +1 -1
- onnx/model.onnx +2 -2
- onnx/model.onnx_data +3 -0
- onnx/model_fp16.onnx +2 -2
- onnx/model_fp16.onnx_data +3 -0
- onnx/model_q4.onnx +2 -2
- onnx/{model_bnb4.onnx → model_q4.onnx_data} +2 -2
- onnx/model_q4f16.onnx +2 -2
- onnx/{model_int8.onnx → model_q4f16.onnx_data} +2 -2
- onnx/model_quantized.onnx +2 -2
- onnx/{model_uint8.onnx → model_quantized.onnx_data} +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +2 -2
.gitattributes
CHANGED
|
@@ -33,3 +33,8 @@ 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
|
| 38 |
+
onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
onnx/model_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
|
@@ -1,12 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_attn_implementation_autoset": true,
|
| 3 |
-
"_name_or_path": "PleIAs/Monad",
|
| 4 |
"architectures": [
|
| 5 |
"LlamaForCausalLM"
|
| 6 |
],
|
| 7 |
"attention_bias": false,
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"bos_token_id": 1,
|
|
|
|
| 10 |
"eos_token_id": 2,
|
| 11 |
"head_dim": 64,
|
| 12 |
"hidden_act": "silu",
|
|
@@ -21,11 +20,26 @@
|
|
| 21 |
"num_key_value_heads": 4,
|
| 22 |
"pretraining_tp": 1,
|
| 23 |
"rms_norm_eps": 1e-05,
|
| 24 |
-
"
|
|
|
|
|
|
|
|
|
|
| 25 |
"rope_theta": 10000,
|
| 26 |
"tie_word_embeddings": true,
|
| 27 |
-
"
|
| 28 |
-
"transformers_version": "4.49.0",
|
| 29 |
"use_cache": true,
|
| 30 |
-
"vocab_size": 8192
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"LlamaForCausalLM"
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": 2,
|
| 10 |
"head_dim": 64,
|
| 11 |
"hidden_act": "silu",
|
|
|
|
| 20 |
"num_key_value_heads": 4,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_parameters": {
|
| 24 |
+
"rope_theta": 10000,
|
| 25 |
+
"rope_type": "default"
|
| 26 |
+
},
|
| 27 |
"rope_theta": 10000,
|
| 28 |
"tie_word_embeddings": true,
|
| 29 |
+
"transformers_version": "5.0.0.dev0",
|
|
|
|
| 30 |
"use_cache": true,
|
| 31 |
+
"vocab_size": 8192,
|
| 32 |
+
"transformers.js_config": {
|
| 33 |
+
"use_external_data_format": {
|
| 34 |
+
"model.onnx": 1,
|
| 35 |
+
"model_fp16.onnx": 1,
|
| 36 |
+
"model_quantized.onnx": 1,
|
| 37 |
+
"model_q4.onnx": 1,
|
| 38 |
+
"model_q4f16.onnx": 1
|
| 39 |
+
},
|
| 40 |
+
"kv_cache_dtype": {
|
| 41 |
+
"q4f16": "float16",
|
| 42 |
+
"fp16": "float16"
|
| 43 |
+
}
|
| 44 |
+
}
|
| 45 |
+
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "5.0.0.dev0"
|
| 6 |
}
|
onnx/model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a6c06b0812fdf586e0cbdc3a8760bf7b91fd1c1e5aebebbbcdf21f066254a88
|
| 3 |
+
size 421087
|
onnx/model.onnx_data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4264517ce25a2d32f4231bccf46c597e7822e11dae7f4d6b30d7c1c547ee61d0
|
| 3 |
+
size 227148800
|
onnx/model_fp16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0059180a76a87e83130d30081ee3711d276128d19409f5ec9bffddb34e577e74
|
| 3 |
+
size 481133
|
onnx/model_fp16.onnx_data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c2c742a6c8e7c8d87166f069ffa7af33a61741cb184fe8936501c98b3330578
|
| 3 |
+
size 113508352
|
onnx/model_q4.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a13355cecc75fde2ad45a842c3ecc1040a83408016d09d4695f8e5ea72608e6b
|
| 3 |
+
size 584663
|
onnx/{model_bnb4.onnx → model_q4.onnx_data}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93a042e3c6c88759b3db48a62bd43c585c95b3fcc3bb8233aebecc59e861afe3
|
| 3 |
+
size 43123712
|
onnx/model_q4f16.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:820851cf9f94f7393d03cf9cbc983de743283e1fbf95b00aeb3df59862e291fb
|
| 3 |
+
size 645593
|
onnx/{model_int8.onnx → model_q4f16.onnx_data}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1650aa9ce902ddfdaf97f33cb5281eb92770e18e8049e4fd14ff6746e5f9ff1d
|
| 3 |
+
size 35127296
|
onnx/model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497f7bf19a0b35603903927ffdc51bac927ca2954e110c6f5966d7485185c60e
|
| 3 |
+
size 1911967
|
onnx/{model_uint8.onnx → model_quantized.onnx_data}
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cde7ba8af8ea6201ba6d1d9de47f7843e73710406b47829831e8a35349353ca6
|
| 3 |
+
size 57279488
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -36,5 +36,5 @@
|
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"extra_special_tokens": {},
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
-
"tokenizer_class": "
|
| 40 |
-
}
|
|
|
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"extra_special_tokens": {},
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 40 |
+
}
|