Hugging Face's logo

SpaceGhost
/
SpaceCode-GGUF

GGUF
gemma4
llama.cpp
unsloth
conversational
Model card Files
xet
 Community
SpaceGhost commited on
Commit
afb7968
·
verified ·
1 Parent(s): 7f2fb54

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (5) hide show
  1. .gitattributes +1 -0
  2. Modelfile +10 -0
  3. README.md +21 -1
  4. config.json +189 -0
  5. gemma-4-E2B-it.Q4_K_M.gguf +3 -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
+ gemma-4-E2B-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Modelfile ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ FROM gemma-4-E2B-it.Q4_K_M.gguf
3
+ TEMPLATE """{{- range $i, $_ := .Messages }}
4
+ {{- $last := eq (len (slice $.Messages $i)) 1 }}
5
+ <|turn>{{ .Role }}
6
+ {{ .Content }}{{ if not $last }}<turn|>
7
+ {{ end }}
8
+ {{- end }}<turn|>
9
+ <|turn>model
10
+ """
README.md CHANGED
@@ -1,3 +1,23 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - gguf
4
+ - llama.cpp
5
+ - unsloth
6
+
7
  ---
8
+
9
+ # SpaceCode-GGUF : GGUF
10
+
11
+ This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
12
+
13
+ **Example usage**:
14
+ - For text only LLMs: `llama-cli -hf SpaceGhost/SpaceCode-GGUF --jinja`
15
+ - For multimodal models: `llama-mtmd-cli -hf SpaceGhost/SpaceCode-GGUF --jinja`
16
+
17
+ ## Available Model files:
18
+ - `gemma-4-E2B-it.Q4_K_M.gguf`
19
+
20
+ ## Ollama
21
+ An Ollama Modelfile is included for easy deployment.
22
+ This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
23
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
config.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": {
6
+ "_name_or_path": "",
7
+ "architectures": null,
8
+ "attention_chunk_size": 12,
9
+ "attention_context_left": 13,
10
+ "attention_context_right": 0,
11
+ "attention_invalid_logits_value": -1000000000.0,
12
+ "attention_logit_cap": 50.0,
13
+ "chunk_size_feed_forward": 0,
14
+ "conv_kernel_size": 5,
15
+ "torch_dtype": "bfloat16",
16
+ "gradient_clipping": 10000000000.0,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 1024,
19
+ "id2label": {
20
+ "0": "LABEL_0",
21
+ "1": "LABEL_1"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "is_encoder_decoder": false,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1
28
+ },
29
+ "model_type": "gemma4_audio",
30
+ "num_attention_heads": 8,
31
+ "num_hidden_layers": 12,
32
+ "output_attentions": false,
33
+ "output_hidden_states": false,
34
+ "output_proj_dims": 1536,
35
+ "problem_type": null,
36
+ "residual_weight": 0.5,
37
+ "return_dict": true,
38
+ "rms_norm_eps": 1e-06,
39
+ "subsampling_conv_channels": [
40
+ 128,
41
+ 32
42
+ ],
43
+ "use_clipped_linears": true
44
+ },
45
+ "audio_token_id": 258881,
46
+ "boa_token_id": 256000,
47
+ "boi_token_id": 255999,
48
+ "torch_dtype": "bfloat16",
49
+ "eoa_token_id": 258883,
50
+ "eoa_token_index": 258883,
51
+ "eoi_token_id": 258882,
52
+ "eos_token_id": 106,
53
+ "image_token_id": 258880,
54
+ "initializer_range": 0.02,
55
+ "model_type": "gemma4",
56
+ "pad_token_id": 0,
57
+ "text_config": {
58
+ "attention_bias": false,
59
+ "attention_dropout": 0.0,
60
+ "attention_k_eq_v": false,
61
+ "bos_token_id": 2,
62
+ "torch_dtype": "bfloat16",
63
+ "enable_moe_block": false,
64
+ "eos_token_id": 1,
65
+ "expert_intermediate_size": null,
66
+ "final_logit_softcapping": 30.0,
67
+ "global_head_dim": 512,
68
+ "head_dim": 256,
69
+ "hidden_activation": "gelu_pytorch_tanh",
70
+ "hidden_size": 1536,
71
+ "hidden_size_per_layer_input": 256,
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 6144,
74
+ "layer_types": [
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "full_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "full_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "full_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "full_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "full_attention"
110
+ ],
111
+ "max_position_embeddings": 131072,
112
+ "model_type": "gemma4_text",
113
+ "moe_intermediate_size": null,
114
+ "num_attention_heads": 8,
115
+ "num_experts": null,
116
+ "num_global_key_value_heads": null,
117
+ "num_hidden_layers": 35,
118
+ "num_key_value_heads": 1,
119
+ "num_kv_shared_layers": 20,
120
+ "pad_token_id": 0,
121
+ "rms_norm_eps": 1e-06,
122
+ "rope_parameters": {
123
+ "full_attention": {
124
+ "partial_rotary_factor": 0.25,
125
+ "rope_theta": 1000000.0,
126
+ "rope_type": "proportional"
127
+ },
128
+ "sliding_attention": {
129
+ "rope_theta": 10000.0,
130
+ "rope_type": "default"
131
+ }
132
+ },
133
+ "sliding_window": 512,
134
+ "tie_word_embeddings": true,
135
+ "top_k_experts": null,
136
+ "use_bidirectional_attention": null,
137
+ "use_cache": true,
138
+ "use_double_wide_mlp": true,
139
+ "vocab_size": 262144,
140
+ "vocab_size_per_layer_input": 262144
141
+ },
142
+ "tie_word_embeddings": true,
143
+ "unsloth_fixed": true,
144
+ "video_token_id": 258884,
145
+ "vision_config": {
146
+ "_name_or_path": "",
147
+ "architectures": null,
148
+ "attention_bias": false,
149
+ "attention_dropout": 0.0,
150
+ "chunk_size_feed_forward": 0,
151
+ "default_output_length": 280,
152
+ "torch_dtype": "bfloat16",
153
+ "global_head_dim": 64,
154
+ "head_dim": 64,
155
+ "hidden_activation": "gelu_pytorch_tanh",
156
+ "hidden_size": 768,
157
+ "id2label": {
158
+ "0": "LABEL_0",
159
+ "1": "LABEL_1"
160
+ },
161
+ "initializer_range": 0.02,
162
+ "intermediate_size": 3072,
163
+ "is_encoder_decoder": false,
164
+ "label2id": {
165
+ "LABEL_0": 0,
166
+ "LABEL_1": 1
167
+ },
168
+ "max_position_embeddings": 131072,
169
+ "model_type": "gemma4_vision",
170
+ "num_attention_heads": 12,
171
+ "num_hidden_layers": 16,
172
+ "num_key_value_heads": 12,
173
+ "output_attentions": false,
174
+ "output_hidden_states": false,
175
+ "patch_size": 16,
176
+ "pooling_kernel_size": 3,
177
+ "position_embedding_size": 10240,
178
+ "problem_type": null,
179
+ "return_dict": true,
180
+ "rms_norm_eps": 1e-06,
181
+ "rope_parameters": {
182
+ "rope_theta": 100.0,
183
+ "rope_type": "default"
184
+ },
185
+ "standardize": false,
186
+ "use_clipped_linears": true
187
+ },
188
+ "vision_soft_tokens_per_image": 280
189
+ }
gemma-4-E2B-it.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c469e837ffca1dea9ab344f61492a8457ef6c560930cd71d94917cb91a7b0e48
3
+ size 3427880384