Hugging Face's logo

turnio
/
medgemma-27b-text-it-FP8-Dynamic

Text Generation
Transformers
Safetensors
gemma3_text
medgemma
medical
fp8
quantized
vllm
llmcompressor
conversational
text-generation-inference
compressed-tensors
Model card Files
xet
 Community
fedme2 commited on
Commit
4083cc5
·
verified ·
1 Parent(s): 1604f93

Upload FP8_DYNAMIC quantized model via llm-compressor

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +47 -0
  3. config.json +153 -0
  4. generation_config.json +11 -0
  5. model-00001-of-00006.safetensors +3 -0
  6. model-00002-of-00006.safetensors +3 -0
  7. model-00003-of-00006.safetensors +3 -0
  8. model-00004-of-00006.safetensors +3 -0
  9. model-00005-of-00006.safetensors +3 -0
  10. model-00006-of-00006.safetensors +3 -0
  11. model.safetensors.index.json +0 -0
  12. recipe.yaml +6 -0
  13. special_tokens_map.json +33 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ 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 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "cache_implementation": "hybrid",
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 1,
13
+ "final_logit_softcapping": null,
14
+ "head_dim": 128,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 5376,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 21504,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "sliding_attention",
25
+ "full_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "full_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention",
80
+ "sliding_attention",
81
+ "sliding_attention"
82
+ ],
83
+ "max_position_embeddings": 131072,
84
+ "model_type": "gemma3_text",
85
+ "num_attention_heads": 32,
86
+ "num_hidden_layers": 62,
87
+ "num_key_value_heads": 16,
88
+ "pad_token_id": 0,
89
+ "quantization_config": {
90
+ "config_groups": {
91
+ "group_0": {
92
+ "format": "float-quantized",
93
+ "input_activations": {
94
+ "actorder": null,
95
+ "block_structure": null,
96
+ "dynamic": true,
97
+ "group_size": null,
98
+ "num_bits": 8,
99
+ "observer": null,
100
+ "observer_kwargs": {},
101
+ "scale_dtype": null,
102
+ "strategy": "token",
103
+ "symmetric": true,
104
+ "type": "float",
105
+ "zp_dtype": null
106
+ },
107
+ "output_activations": null,
108
+ "targets": [
109
+ "Linear"
110
+ ],
111
+ "weights": {
112
+ "actorder": null,
113
+ "block_structure": null,
114
+ "dynamic": false,
115
+ "group_size": null,
116
+ "num_bits": 8,
117
+ "observer": "minmax",
118
+ "observer_kwargs": {},
119
+ "scale_dtype": null,
120
+ "strategy": "channel",
121
+ "symmetric": true,
122
+ "type": "float",
123
+ "zp_dtype": null
124
+ }
125
+ }
126
+ },
127
+ "format": "float-quantized",
128
+ "global_compression_ratio": null,
129
+ "ignore": [
130
+ "lm_head"
131
+ ],
132
+ "kv_cache_scheme": null,
133
+ "quant_method": "compressed-tensors",
134
+ "quantization_status": "compressed",
135
+ "sparsity_config": {},
136
+ "transform_config": {},
137
+ "version": "0.13.0"
138
+ },
139
+ "query_pre_attn_scalar": 168,
140
+ "rms_norm_eps": 1e-06,
141
+ "rope_local_base_freq": 10000,
142
+ "rope_scaling": {
143
+ "factor": 8.0,
144
+ "rope_type": "linear"
145
+ },
146
+ "rope_theta": 1000000,
147
+ "sliding_window": 1024,
148
+ "sliding_window_pattern": 6,
149
+ "transformers_version": "4.57.3",
150
+ "use_bidirectional_attention": false,
151
+ "use_cache": true,
152
+ "vocab_size": 262144
153
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cache_implementation": "hybrid",
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106
7
+ ],
8
+ "top_k": 64,
9
+ "top_p": 0.95,
10
+ "transformers_version": "4.57.3"
11
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8143910d58b172f1db39f602529bd50ea9472966463b3c73a7e57efd9b015dc
3
+ size 4949894464
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:840b6e39cc1235d7c5459c8a4625b64573262189818ca4dbef5cb11b3dab8932
3
+ size 4956558056
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e18819df32b82d158aa4d2fc316d110751b019a74f2234f58310eda0484544
3
+ size 4956558160
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0cb9fdb5a9b61f5e01ac449f8199f489975381841dde994415d818d5e07c890
3
+ size 4956558160
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873b29dfc6d2f7c71b95e57357db2556035625829c47bd49bf58ac77f954fdd4
3
+ size 4956558160
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907817b077e6cfdc7baac024d020c9b19c1ae00b4ef1c21cfee11034126867f7
3
+ size 3651340328
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: FP8_DYNAMIC
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 sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff