Upload optimized ONNX model
Browse files- .gitattributes +4 -0
- chat_template.jinja +37 -0
- config.json +70 -0
- onnx/model.onnx +3 -0
- onnx/model.onnx_data +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_fp16.onnx_data +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4.onnx_data +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_q4f16.onnx_data +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,7 @@ 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
|
chat_template.jinja
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{- bos_token -}}
|
2 |
+
{%- set system_prompt = "" -%}
|
3 |
+
{%- set ns = namespace(system_prompt="") -%}
|
4 |
+
{%- if messages[0]["role"] == "system" -%}
|
5 |
+
{%- set ns.system_prompt = messages[0]["content"] -%}
|
6 |
+
{%- set messages = messages[1:] -%}
|
7 |
+
{%- endif -%}
|
8 |
+
{%- if tools -%}
|
9 |
+
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
|
10 |
+
{%- for tool in tools -%}
|
11 |
+
{%- if tool is not string -%}
|
12 |
+
{%- set tool = tool | tojson -%}
|
13 |
+
{%- endif -%}
|
14 |
+
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
15 |
+
{%- if not loop.last -%}
|
16 |
+
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
17 |
+
{%- endif -%}
|
18 |
+
{%- endfor -%}
|
19 |
+
{%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
|
20 |
+
{%- endif -%}
|
21 |
+
{%- if ns.system_prompt -%}
|
22 |
+
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
23 |
+
{%- endif -%}
|
24 |
+
{%- for message in messages -%}
|
25 |
+
{{- "<|im_start|>" + message["role"] + "\n" -}}
|
26 |
+
{%- set content = message["content"] -%}
|
27 |
+
{%- if content is not string -%}
|
28 |
+
{%- set content = content | tojson -%}
|
29 |
+
{%- endif -%}
|
30 |
+
{%- if message["role"] == "tool" -%}
|
31 |
+
{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
|
32 |
+
{%- endif -%}
|
33 |
+
{{- content + "<|im_end|>\n" -}}
|
34 |
+
{%- endfor -%}
|
35 |
+
{%- if add_generation_prompt -%}
|
36 |
+
{{- "<|im_start|>assistant\n" -}}
|
37 |
+
{%- endif -%}
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Lfm2ForCausalLM"
|
4 |
+
],
|
5 |
+
"block_auto_adjust_ff_dim": true,
|
6 |
+
"block_dim": 1024,
|
7 |
+
"block_ff_dim": 6656,
|
8 |
+
"block_ffn_dim_multiplier": 1.0,
|
9 |
+
"block_mlp_init_scale": 1.0,
|
10 |
+
"block_multiple_of": 256,
|
11 |
+
"block_norm_eps": 1e-05,
|
12 |
+
"block_out_init_scale": 1.0,
|
13 |
+
"block_use_swiglu": true,
|
14 |
+
"block_use_xavier_init": true,
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"conv_L_cache": 3,
|
17 |
+
"conv_bias": false,
|
18 |
+
"conv_dim": 1024,
|
19 |
+
"conv_dim_out": 1024,
|
20 |
+
"conv_use_xavier_init": true,
|
21 |
+
"eos_token_id": 7,
|
22 |
+
"hidden_size": 1024,
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 6656,
|
25 |
+
"layer_types": [
|
26 |
+
"conv",
|
27 |
+
"conv",
|
28 |
+
"full_attention",
|
29 |
+
"conv",
|
30 |
+
"conv",
|
31 |
+
"full_attention",
|
32 |
+
"conv",
|
33 |
+
"conv",
|
34 |
+
"full_attention",
|
35 |
+
"conv",
|
36 |
+
"full_attention",
|
37 |
+
"conv",
|
38 |
+
"full_attention",
|
39 |
+
"conv",
|
40 |
+
"full_attention",
|
41 |
+
"conv"
|
42 |
+
],
|
43 |
+
"max_position_embeddings": 128000,
|
44 |
+
"model_type": "lfm2",
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"num_attention_heads": 16,
|
47 |
+
"num_heads": 16,
|
48 |
+
"num_hidden_layers": 16,
|
49 |
+
"num_key_value_heads": 8,
|
50 |
+
"pad_token_id": 0,
|
51 |
+
"rope_theta": 1000000.0,
|
52 |
+
"torch_dtype": "bfloat16",
|
53 |
+
"transformers_version": "4.56.0.dev0",
|
54 |
+
"unsloth_version": "2025.8.1",
|
55 |
+
"use_cache": true,
|
56 |
+
"use_pos_enc": true,
|
57 |
+
"vocab_size": 93083,
|
58 |
+
"transformers.js_config": {
|
59 |
+
"use_external_data_format": {
|
60 |
+
"model.onnx": 1,
|
61 |
+
"model_fp16.onnx": 1,
|
62 |
+
"model_q4.onnx": 1,
|
63 |
+
"model_q4f16.onnx": 1
|
64 |
+
},
|
65 |
+
"kv_cache_dtype": {
|
66 |
+
"q4f16": "float16",
|
67 |
+
"fp16": "float16"
|
68 |
+
}
|
69 |
+
}
|
70 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:029dcf12cd579dd4368649aa13ed9aa83a721def3605022a897ca57c659051e3
|
3 |
+
size 149015
|
onnx/model.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302683df138d394fc9f71674e16276ed4c76843c68288f433d2bece06d88642b
|
3 |
+
size 1563533312
|
onnx/model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fed3345f5185bb9282f755100c81cd856f2ec8f7ca17dc34acfecbd34aefc60
|
3 |
+
size 148241
|
onnx/model_fp16.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0217ba36d78617ab7ffa086d977a55621b568adb8d7bc4830398d92e27b3ab4e
|
3 |
+
size 781766656
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d9cda2dc8e4922090361f819321963caaa2a4077323599b8128a3d360220513
|
3 |
+
size 182692
|
onnx/model_q4.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56108db379a579a201186f677589aa53fc1660effb8d00aff88448fc683f2a1e
|
3 |
+
size 593862656
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff91833a6af7ade9c8c824d2565575918e6d0b9a3b8b9c895e2e620c0f5a4148
|
3 |
+
size 181992
|
onnx/model_q4f16.onnx_data
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b82059e5933f790cedbc447fad86ac815384ad5d21204c03a26a9d231b0cafb
|
3 |
+
size 368758784
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|