Hugging Face's logo

LoligoGames
/
project_amelia

Text Generation
Safetensors
gemma3_text
Persona
llama-factory
conversational
Model card Files
xet
 Community
Campis commited on
Commit
dea5d49
·
verified ·
1 Parent(s): 379e5c6

Upload LlamaForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +2 -1
  2. config.json +29 -27
  3. generation_config.json +7 -8
  4. model.safetensors +2 -2
README.md CHANGED
@@ -4,4 +4,5 @@ base_model:
4
  pipeline_tag: text-generation
5
  tags:
6
  - Persona
7
- ---
 
 
4
  pipeline_tag: text-generation
5
  tags:
6
  - Persona
7
+ - llama-factory
8
+ ---
config.json CHANGED
@@ -1,37 +1,39 @@
1
  {
2
  "architectures": [
3
- "Gemma3ForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
  "eos_token_id": [
11
- 1,
12
- 106
 
13
  ],
14
- "final_logit_softcapping": null,
15
- "head_dim": 256,
16
- "hidden_activation": "gelu_pytorch_tanh",
17
- "hidden_size": 1152,
18
  "initializer_range": 0.02,
19
- "intermediate_size": 6912,
20
- "max_position_embeddings": 32768,
21
- "model_type": "gemma3_text",
22
- "num_attention_heads": 4,
23
- "num_hidden_layers": 26,
24
- "num_key_value_heads": 1,
25
- "pad_token_id": 0,
26
- "query_pre_attn_scalar": 256,
27
- "rms_norm_eps": 1e-06,
28
- "rope_local_base_freq": 10000,
29
- "rope_scaling": null,
30
- "rope_theta": 1000000,
31
- "sliding_window": 512,
32
- "sliding_window_pattern": 6,
33
- "torch_dtype": "float16",
34
- "transformers_version": "4.52.3",
 
 
 
 
35
  "use_cache": true,
36
- "vocab_size": 262144
37
  }
 
1
  {
2
  "architectures": [
3
+ "LlamaForCausalLM"
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
 
 
8
  "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
  ],
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
 
16
  "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 16,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 32.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.52.4",
37
  "use_cache": true,
38
+ "vocab_size": 128256
39
  }
generation_config.json CHANGED
@@ -1,13 +1,12 @@
1
  {
2
- "bos_token_id": 2,
3
- "cache_implementation": "hybrid",
4
  "do_sample": true,
5
  "eos_token_id": [
6
- 1,
7
- 106
 
8
  ],
9
- "pad_token_id": 0,
10
- "top_k": 64,
11
- "top_p": 0.95,
12
- "transformers_version": "4.52.3"
13
  }
 
1
  {
2
+ "bos_token_id": 128000,
 
3
  "do_sample": true,
4
  "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
  ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.52.4"
 
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:930d802e836cb3098656559fad73dc4beae161601009ceacb481c0e4507a4ddb
3
- size 1999810864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7d2773b6f6d188aaf712bec880ead587c9773c1a04da2b077faae7ef61ef23
3
+ size 2471645608