LoneStriker commited on
Commit
b3275c1
1 Parent(s): 0729eaa

Upload folder using huggingface_hub

Browse files
.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
README.md ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ extra_gated_heading: Access Gemma on Hugging Face
4
+ extra_gated_prompt: >-
5
+ To access Gemma on Hugging Face, you’re required to review and agree to
6
+ Google’s usage license. To do this, please ensure you’re logged-in to Hugging
7
+ Face and click below. Requests are processed immediately.
8
+ extra_gated_button_content: Acknowledge license
9
+ license: other
10
+ license_name: gemma-terms-of-use
11
+ license_link: https://ai.google.dev/gemma/terms
12
+ base_model:
13
+ - google/gemma-2b
14
+ datasets:
15
+ - vicgalle/alpaca-gpt4
16
+ ---
17
+
18
+ ![image/webp](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/uwPjZeV-JQwKWrI7nHg4w.webp)
19
+
20
+ # Gemmalpaca-2B
21
+
22
+ This is gemma-2b model supervised fine-tuned on the [vicgalle/alpaca-gpt4](https://huggingface.co/datasets/vicgalle/alpaca-gpt4) dataset. It outperforms gemma-2b-it, Google's chat version, on Nous' benchmark suite.
23
+
24
+ It's mostly a test to see how fine-tuning works with Gemma models on a well-known dataset. It turned out better than expected. :)
25
+
26
+ ## 🔍 Applications
27
+
28
+ This model has a context length of 8k. I recommend using it with the Alpaca chat template and NOT the Gemma Instruct template (works perfectly with LM Studio). You also want to add `</s>` as a stop token.
29
+
30
+ ## ⚡ Quantized models
31
+
32
+ * **GGUF**: https://huggingface.co/mlabonne/Gemmalpaca-2B-GGUF
33
+
34
+ ## 🏆 Evaluation
35
+
36
+ ### Nous
37
+
38
+ Gemmalpaca-2B outperforms gemma-2b and gemma-2b-it on Nous' benchmark suite (evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval)). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
39
+
40
+ | Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
41
+ |---|---:|---:|---:|---:|---:|
42
+ | [mlabonne/Gemmalpaca-2B](https://huggingface.co/mlabonne/Gemmalpaca-2B) [📄](https://gist.github.com/mlabonne/4b638752fc3227df566f9562064cb864) | 38.39 | 24.48 | 51.22 | 47.02 | 30.85 |
43
+ | [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) [📄](https://gist.github.com/mlabonne/db0761e74175573292acf497da9e5d95) | 36.1 | 23.76 | 43.6 | 47.64 | 29.41 |
44
+ | [google/gemma-2b](https://huggingface.co/google/gemma-2b) [📄](https://gist.github.com/mlabonne/7df1f238c515a5f63a750c8792cef59e) | 34.26 | 22.7 | 43.35 | 39.96 | 31.03 |
45
+
46
+ ## 🧩 Configuration
47
+
48
+ It was trained using [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) with the following configuration.
49
+
50
+ ```yaml
51
+ base_model: alpindale/gemma-2b
52
+ model_type: GemmaForCausalLM
53
+ tokenizer_type: GemmaTokenizer
54
+
55
+ load_in_8bit: false
56
+ load_in_4bit: true
57
+ strict: false
58
+
59
+ datasets:
60
+ - path: vicgalle/alpaca-gpt4
61
+ type: alpaca
62
+
63
+ dataset_prepared_path:
64
+ val_set_size: 0.01
65
+ output_dir: ./out
66
+
67
+ sequence_len: 2048
68
+ sample_packing: true
69
+ pad_to_sequence_len: true
70
+
71
+ adapter: qlora
72
+ lora_model_dir:
73
+ lora_r: 32
74
+ lora_alpha: 64
75
+ lora_dropout: 0.05
76
+ lora_target_linear: true
77
+
78
+ wandb_project: axolotl
79
+ wandb_entity:
80
+ wandb_watch:
81
+ wandb_name:
82
+ wandb_log_model:
83
+
84
+ gradient_accumulation_steps: 4
85
+ micro_batch_size: 2
86
+ num_epochs: 3
87
+ optimizer: adamw_bnb_8bit
88
+ lr_scheduler: cosine
89
+ learning_rate: 0.0002
90
+
91
+ train_on_inputs: false
92
+ group_by_length: false
93
+ bf16: auto
94
+ fp16:
95
+ tf32: false
96
+
97
+ gradient_checkpointing: true
98
+ early_stopping_patience:
99
+ resume_from_checkpoint:
100
+ local_rank:
101
+ logging_steps: 1
102
+ xformers_attention:
103
+ flash_attention:
104
+
105
+ warmup_steps: 10
106
+ evals_per_epoch: 4
107
+ eval_table_size:
108
+ eval_table_max_new_tokens: 128
109
+ saves_per_epoch: 1
110
+ debug:
111
+ deepspeed:
112
+ weight_decay: 0.1
113
+ fsdp:
114
+ fsdp_config:
115
+ special_tokens:
116
+ bos_token: <s>
117
+ eos_token: </s>
118
+ unk_token: <unk>
119
+ ```
120
+
121
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alpindale/gemma-2b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 16384,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.39.0.dev0",
26
+ "use_cache": true,
27
+ "vocab_size": 256000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5012344832
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
89
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
90
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.norm.weight": "model-00002-of-00002.safetensors"
170
+ }
171
+ }
output.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5497f5cd1d55570a4fd41e17a25c1fd68c972d6dd14c1dd95a6fc9e67d284f6
3
+ size 2954456736
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
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
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d908b4f9326e0998815690e325b6abbd378978553e10627924dd825db7e243
3
+ size 17477553
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
3
+ size 4241111
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<bos>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "<eos>",
41
+ "legacy": null,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "sp_model_kwargs": {},
45
+ "spaces_between_special_tokens": false,
46
+ "tokenizer_class": "GemmaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": false
49
+ }