Hugging Face's logo

Electronik3
/
T-Lab-Alignment-Test

Safetensors
Model card Files
xet
Community
Electronik3 commited on
Commit
a965588
·
verified ·
1 Parent(s): 3f47b64

Upload 5 files

Browse files
Files changed (5) hide show
  1. reward_model/config.json +45 -0
  2. reward_model/model.safetensors +3 -0
  3. rlhf_policy_model/config.json +39 -0
  4. rlhf_policy_model/generation_config.json +7 -0
  5. rlhf_policy_model/model.safetensors +3 -0
reward_model/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "id2label": {
14
+ "0": "LABEL_0"
15
+ },
16
+ "initializer_range": 0.041666666666666664,
17
+ "intermediate_size": 1536,
18
+ "is_llama_config": true,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "max_position_embeddings": 8192,
23
+ "mlp_bias": false,
24
+ "model_type": "llama",
25
+ "num_attention_heads": 9,
26
+ "num_hidden_layers": 30,
27
+ "num_key_value_heads": 3,
28
+ "pad_token_id": 2,
29
+ "pretraining_tp": 1,
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_interleaved": false,
32
+ "rope_scaling": null,
33
+ "rope_theta": 100000,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "float32",
36
+ "transformers.js_config": {
37
+ "kv_cache_dtype": {
38
+ "fp16": "float16",
39
+ "q4f16": "float16"
40
+ }
41
+ },
42
+ "transformers_version": "4.47.1",
43
+ "use_cache": true,
44
+ "vocab_size": 49152
45
+ }
reward_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7add60da38b179ed1e53bf378ab74cc5a96b5e138acb9bc8e2ff126ef9406442
3
+ size 538092792
rlhf_policy_model/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.041666666666666664,
14
+ "intermediate_size": 1536,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 9,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "float32",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.47.1",
37
+ "use_cache": true,
38
+ "vocab_size": 49152
39
+ }
rlhf_policy_model/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.47.1"
7
+ }
rlhf_policy_model/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55442a797c02c1a904e23df5d0f727c507f7cdbab7e7e35275d220ee865d9eff
3
+ size 538090408