Hugging Face's logo

RASMUS
/
Ahma-2-4B-Instruct-ONNX

ONNX
gemma3_text
Model card Files
xet
 Community
RASMUS commited on
Commit
1db93be
·
verified ·
1 Parent(s): fcc61fb

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +12 -0
  2. chat_template.jinja +47 -0
  3. config.json +84 -0
  4. generation_config.json +14 -0
  5. onnx/model_q4f16.onnx +3 -0
  6. onnx/model_q4f16.onnx_data +3 -0
  7. onnx/model_q4f16.onnx_data_1 +3 -0
  8. onnx/model_q4f16.onnx_data_10 +3 -0
  9. onnx/model_q4f16.onnx_data_2 +3 -0
  10. onnx/model_q4f16.onnx_data_3 +3 -0
  11. onnx/model_q4f16.onnx_data_4 +3 -0
  12. onnx/model_q4f16.onnx_data_5 +3 -0
  13. onnx/model_q4f16.onnx_data_6 +3 -0
  14. onnx/model_q4f16.onnx_data_7 +3 -0
  15. onnx/model_q4f16.onnx_data_8 +3 -0
  16. onnx/model_q4f16.onnx_data_9 +3 -0
  17. special_tokens_map.json +33 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model_q4f16.onnx_data_10 filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model_q4f16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
40
+ onnx/model_q4f16.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
41
+ onnx/model_q4f16.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
42
+ onnx/model_q4f16.onnx_data_5 filter=lfs diff=lfs merge=lfs -text
43
+ onnx/model_q4f16.onnx_data_6 filter=lfs diff=lfs merge=lfs -text
44
+ onnx/model_q4f16.onnx_data_7 filter=lfs diff=lfs merge=lfs -text
45
+ onnx/model_q4f16.onnx_data_8 filter=lfs diff=lfs merge=lfs -text
46
+ onnx/model_q4f16.onnx_data_9 filter=lfs diff=lfs merge=lfs -text
47
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{ '<start_of_turn>model
46
+ ' }}
47
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
18
+ "layer_types": [
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention"
53
+ ],
54
+ "max_position_embeddings": 131072,
55
+ "model_type": "gemma3_text",
56
+ "num_attention_heads": 8,
57
+ "num_hidden_layers": 34,
58
+ "num_key_value_heads": 4,
59
+ "pad_token_id": 0,
60
+ "query_pre_attn_scalar": 256,
61
+ "rms_norm_eps": 1e-06,
62
+ "rope_local_base_freq": 10000.0,
63
+ "rope_scaling": {
64
+ "factor": 8.0,
65
+ "rope_type": "linear"
66
+ },
67
+ "rope_theta": 1000000.0,
68
+ "sliding_window": 1024,
69
+ "torch_dtype": "float16",
70
+ "transformers_version": "4.53.3",
71
+ "unsloth_version": "2025.10.2",
72
+ "use_cache": true,
73
+ "vocab_size": 262144,
74
+ "transformers.js_config": {
75
+ "use_external_data_format": {
76
+ "model_fp16.onnx": true,
77
+ "model_q4f16.onnx": 11
78
+ },
79
+ "kv_cache_dtype": {
80
+ "fp16": "float16",
81
+ "q4f16": "float32"
82
+ }
83
+ }
84
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "max_length": 131072,
10
+ "pad_token_id": 0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.53.3"
14
+ }
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee093fe703ed96d06abb98b64e649ef699d5fcb6de3a815e0e4dd3db8d394d5
3
+ size 2065944
onnx/model_q4f16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e436ebd7c591519bf7fdf04d9618764beb38302c08dc0256444e3b5fd24c7e48
3
+ size 1472512
onnx/model_q4f16.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d56dc500575ddf284ae11d31f84b33c61a1b44cf45bbdff5c0db3791e611d33
3
+ size 335544320
onnx/model_q4f16.onnx_data_10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b4ecaca8c47fe1b5a839968f74376990103fd46c13a3418cf84b207ebe7839
3
+ size 23592960
onnx/model_q4f16.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2cdba6e2d3f50d0f71c5905ee7ac5a6340020e7a7a004fd47c8d107ca94952f
3
+ size 268267520
onnx/model_q4f16.onnx_data_3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a60e27b4f6d193f768cd4e09f6e51f17e53865e5df88f6a7d4d0fee63b3ab18
3
+ size 258129920
onnx/model_q4f16.onnx_data_4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e4cbdfd8af185fd7f7d3373a178d45ad3c478abae1cae4e69249f75c2455bf
3
+ size 266547200
onnx/model_q4f16.onnx_data_5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a51db27cad37ae5af9ebc214625f76a4376818e34a856dec272961102bef4a8d
3
+ size 266547200
onnx/model_q4f16.onnx_data_6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf417502c8b76bed6296bbe217da5205e66c2f31fd61dd5ec5942357a652769
3
+ size 266547200
onnx/model_q4f16.onnx_data_7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73c4627cd4c4b7ed831cc2c4b85c80e0d50c5350baae839f65c4e155f216c0c4
3
+ size 260935680
onnx/model_q4f16.onnx_data_8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdc8be33ee62f6fc37703fe97bdbb549557eb753b01ff007f51b763222365bf
3
+ size 143093760
onnx/model_q4f16.onnx_data_9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031c5c45f681e2e56412f17517bd6d59b6855005a2dfcf01d03325dca1e30e34
3
+ size 335544320
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4201e7b539fef153e1fe3058db39e600717b3323fee690d37e92fa52fb2b5af2
3
+ size 33384667
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff