Hugging Face's logo

sagsan
/
snoopshpear

Text Generation
Transformers
Safetensors
qwen2
conversational
text-generation-inference
Model card Files
xet
 Community
sagsan commited on
Commit
dcd9e00
·
verified ·
1 Parent(s): b618366

Final SnoopShepear CLM fine-tuned model

Browse files
Files changed (3) hide show
  1. config.json +46 -38
  2. generation_config.json +8 -4
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,46 +1,54 @@
1
  {
2
- "_num_labels": 1,
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
  "dtype": "float32",
10
- "embd_pdrop": 0.1,
11
- "eos_token_id": 50256,
12
- "id2label": {
13
- "0": "LABEL_0"
14
- },
15
  "initializer_range": 0.02,
16
- "label2id": {
17
- "LABEL_0": 0
18
- },
19
- "layer_norm_epsilon": 1e-05,
20
- "model_type": "gpt2",
21
- "n_ctx": 1024,
22
- "n_embd": 768,
23
- "n_head": 12,
24
- "n_inner": null,
25
- "n_layer": 6,
26
- "n_positions": 1024,
27
- "pad_token_id": 50256,
28
- "reorder_and_upcast_attn": false,
29
- "resid_pdrop": 0.1,
30
- "scale_attn_by_inverse_layer_idx": false,
31
- "scale_attn_weights": true,
32
- "summary_activation": null,
33
- "summary_first_dropout": 0.1,
34
- "summary_proj_to_labels": true,
35
- "summary_type": "cls_index",
36
- "summary_use_proj": true,
37
- "task_specific_params": {
38
- "text-generation": {
39
- "do_sample": true,
40
- "max_length": 50
41
- }
42
- },
 
 
 
 
 
 
 
 
 
 
 
 
43
  "transformers_version": "4.57.1",
44
  "use_cache": true,
45
- "vocab_size": 50258
 
46
  }
 
1
  {
 
 
2
  "architectures": [
3
+ "Qwen2ForCausalLM"
4
  ],
5
+ "attention_dropout": 0.0,
 
6
  "dtype": "float32",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 896,
 
 
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 4864,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention"
37
+ ],
38
+ "max_position_embeddings": 32768,
39
+ "max_window_layers": 24,
40
+ "model_type": "qwen2",
41
+ "num_attention_heads": 14,
42
+ "num_hidden_layers": 24,
43
+ "num_key_value_heads": 2,
44
+ "pad_token_id": 151645,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": null,
49
+ "tie_word_embeddings": true,
50
  "transformers_version": "4.57.1",
51
  "use_cache": true,
52
+ "use_sliding_window": false,
53
+ "vocab_size": 151647
54
  }
generation_config.json CHANGED
@@ -1,9 +1,13 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
  "eos_token_id": [
5
- 50256
 
6
  ],
7
- "pad_token_id": 50256,
 
 
 
 
8
  "transformers_version": "4.57.1"
9
  }
 
1
  {
2
+ "do_sample": true,
 
3
  "eos_token_id": [
4
+ 151645,
5
+ 151643
6
  ],
7
+ "pad_token_id": 151645,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
  "transformers_version": "4.57.1"
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8423d3eebbb6c1031e3a621148d30cc46172b2500ce457cd4129c0d9d1922a42
3
- size 327661000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351487b09dfd4d518134ec4887f3ac23c49c8f4a2a421336a013c373e08ac9dd
3
+ size 1975127696