Hugging Face's logo

charlesLoder
/
gemma-3-1b-it-q4f16_1-MLC

Model card Files
xet
Community
charlesLoder commited on
Commit
f191a57
·
verified ·
1 Parent(s): e8ed175

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. mlc-chat-config.json +117 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_10.bin +3 -0
  7. params_shard_11.bin +3 -0
  8. params_shard_12.bin +3 -0
  9. params_shard_13.bin +3 -0
  10. params_shard_14.bin +3 -0
  11. params_shard_2.bin +3 -0
  12. params_shard_3.bin +3 -0
  13. params_shard_4.bin +3 -0
  14. params_shard_5.bin +3 -0
  15. params_shard_6.bin +3 -0
  16. params_shard_7.bin +3 -0
  17. params_shard_8.bin +3 -0
  18. params_shard_9.bin +3 -0
  19. tensor-cache.json +0 -0
  20. tokenizer.json +3 -0
  21. tokenizer.model +3 -0
  22. 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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
mlc-chat-config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "gemma3_text",
4
+ "quantization": "q4f16_1",
5
+ "model_config": {
6
+ "text_config": {
7
+ "hidden_size": 1152,
8
+ "intermediate_size": 6912,
9
+ "num_hidden_layers": 26,
10
+ "attention_bias": false,
11
+ "num_attention_heads": 4,
12
+ "num_key_value_heads": 1,
13
+ "head_dim": 256,
14
+ "rms_norm_eps": 1e-06,
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "position_embedding_base": 1000000,
17
+ "rope_scaling": null,
18
+ "context_window_size": 8192,
19
+ "prefill_chunk_size": 8192,
20
+ "query_pre_attn_scalar": 256,
21
+ "sliding_window_size": 512,
22
+ "kwargs": {
23
+ "architectures": [
24
+ "Gemma3ForCausalLM"
25
+ ],
26
+ "attention_dropout": 0.0,
27
+ "attn_logit_softcapping": null,
28
+ "bos_token_id": 2,
29
+ "cache_implementation": "hybrid",
30
+ "eos_token_id": [
31
+ 1,
32
+ 106
33
+ ],
34
+ "final_logit_softcapping": null,
35
+ "initializer_range": 0.02,
36
+ "max_position_embeddings": 32768,
37
+ "model_type": "gemma3_text",
38
+ "pad_token_id": 0,
39
+ "rope_local_base_freq": 10000,
40
+ "sliding_window": 512,
41
+ "sliding_window_pattern": 6,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.50.0.dev0",
44
+ "use_cache": true
45
+ }
46
+ },
47
+ "vocab_size": 262144,
48
+ "tensor_parallel_shards": 1,
49
+ "max_batch_size": 128,
50
+ "context_window_size": 8192,
51
+ "sliding_window_size": 512,
52
+ "prefill_chunk_size": 8192,
53
+ "is_text_model": true
54
+ },
55
+ "vocab_size": 262144,
56
+ "context_window_size": 8192,
57
+ "sliding_window_size": 512,
58
+ "prefill_chunk_size": 8192,
59
+ "attention_sink_size": -1,
60
+ "tensor_parallel_shards": 1,
61
+ "pipeline_parallel_stages": 1,
62
+ "temperature": 1.0,
63
+ "presence_penalty": 0.0,
64
+ "frequency_penalty": 0.0,
65
+ "repetition_penalty": 1.0,
66
+ "top_p": 0.95,
67
+ "tokenizer_files": [
68
+ "tokenizer.model",
69
+ "tokenizer.json",
70
+ "added_tokens.json",
71
+ "tokenizer_config.json"
72
+ ],
73
+ "tokenizer_info": {
74
+ "token_postproc_method": "byte_fallback",
75
+ "prepend_space_in_encode": false,
76
+ "strip_space_in_decode": false
77
+ },
78
+ "conv_template": {
79
+ "name": "gemma3_instruction",
80
+ "system_template": "{system_message}",
81
+ "system_message": "",
82
+ "system_prefix_token_ids": [
83
+ 2
84
+ ],
85
+ "add_role_after_system_message": true,
86
+ "roles": {
87
+ "user": "<start_of_turn>user",
88
+ "assistant": "<start_of_turn>model"
89
+ },
90
+ "role_templates": {
91
+ "user": "{user_message}",
92
+ "assistant": "{assistant_message}",
93
+ "tool": "{tool_message}"
94
+ },
95
+ "messages": [],
96
+ "seps": [
97
+ "<end_of_turn>\n"
98
+ ],
99
+ "role_content_sep": "\n",
100
+ "role_empty_sep": "\n",
101
+ "stop_str": [
102
+ "<end_of_turn>"
103
+ ],
104
+ "stop_token_ids": [
105
+ 1,
106
+ 106
107
+ ],
108
+ "function_string": "",
109
+ "use_function_calling": false
110
+ },
111
+ "pad_token_id": 0,
112
+ "bos_token_id": 2,
113
+ "eos_token_id": [
114
+ 1,
115
+ 106
116
+ ]
117
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0167d3222e5c58f11949a423d1c9ddc027c534d9e2e409cac572f3be73e51df
3
+ size 150994944
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde7508d8160be50315b7daad52f24e2976bbd59dce8441105588253f901090b
3
+ size 33150976
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b373b3e191ca63c9d6df22257df415224061c3bf8e559f017e6e631294a302
3
+ size 30212096
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7b481c5f77ab08ab2faaf9f9e0d87e177e0a3b62ac1a33cdbb52526852462e
3
+ size 30212096
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12324a75f36cd5f562bd006709cf18b3a23a913c9d6f10056f1603c2be4a2ef8
3
+ size 30212096
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39ab8d5ea86b3fb0d180826bc8fe77c693faa3fe199506461dcb54b5672ae01
3
+ size 30212096
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd55f35efa13192d11d36594b5f7f3210e489448c2c6b28918829be790c61ae
3
+ size 15106048
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7849dca237392750a19e6c6b6da9aac9478044c890a3d0514c00a3eb3c3156c2
3
+ size 31043840
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df7a6e261d25ce77787e9327d40b579f26e19f86a04131df572d65c1a1ec21c
3
+ size 30212096
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c16e66de7112989d3e5a2658bea67aa73e99b64d6848210e029034b0e632650
3
+ size 30212096
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:873077ef7e60a09cbccbb3933ace39ddd91083bddc1b16cd2a814df91670f16e
3
+ size 30212096
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43efb4806f76097c0ad52f21e7f9a239d0b3b8cbf97915438a676e7526f12d8
3
+ size 30212096
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add0b861ef1ede2420867f388c41c2555b314781d6a7e5f242c4b27d0a82466c
3
+ size 30212096
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a17a38b781b7b2e5b859fdafe59aab8d194029005393202fe785552c69193f7
3
+ size 30212096
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74732e256024ac734ed4d056aad1b64d90b8033403e0ab6d655443d980586e67
3
+ size 30212096
tensor-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff