Hugging Face's logo

ElMagoRubio
/
SmolLM2-360M-Instruct-lora

PEFT
Safetensors
llama
Model card Files
xet
Community
ElMagoRubio commited on
Commit
d744f56
·
verified ·
1 Parent(s): 174589a

Versión completa del modelo

Browse files
Files changed (3) hide show
  1. config.json +31 -25
  2. generation_config.json +3 -3
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,32 +1,38 @@
1
  {
2
  "architectures": [
3
- "T5ForConditionalGeneration"
4
  ],
5
- "classifier_dropout": 0.0,
6
- "d_ff": 2816,
7
- "d_kv": 64,
8
- "d_model": 1024,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "gelu_new",
11
- "dropout_rate": 0.1,
12
- "eos_token_id": 1,
13
- "feed_forward_proj": "gated-gelu",
14
- "initializer_factor": 1.0,
15
- "is_encoder_decoder": true,
16
- "is_gated_act": true,
17
- "layer_norm_epsilon": 1e-06,
18
- "model_type": "t5",
19
- "n_positions": 512,
20
- "num_decoder_layers": 24,
21
- "num_heads": 16,
22
- "num_layers": 24,
23
- "output_past": true,
24
- "pad_token_id": 0,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
27
- "tie_word_embeddings": false,
28
  "torch_dtype": "float32",
 
 
 
 
 
 
29
  "transformers_version": "4.50.3",
30
  "use_cache": true,
31
- "vocab_size": 32128
32
  }
 
1
  {
2
  "architectures": [
3
+ "LlamaForCausalLM"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 2560,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 15,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 5,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
  "torch_dtype": "float32",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "fp16": "float16",
32
+ "q4f16": "float16"
33
+ }
34
+ },
35
  "transformers_version": "4.50.3",
36
  "use_cache": true,
37
+ "vocab_size": 49152
38
  }
generation_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
  "transformers_version": "4.50.3"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
  "transformers_version": "4.50.3"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
3
- size 3132668808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7319b2ca1aa8f596b5f6e92cb12fe10ea5129025699acba077f36e7460d51406
3
+ size 1447317080