ehristoforu commited on
Commit
8d3ed09
1 Parent(s): 0082fa5

Trained with Unsloth

Browse files
Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +31 -0
  3. generation_config.json +15 -0
  4. pytorch_model.bin +3 -0
README.md CHANGED
@@ -9,6 +9,7 @@ tags:
9
  - unsloth
10
  - qwen2
11
  - trl
 
12
  ---
13
 
14
  # Uploaded model
 
9
  - unsloth
10
  - qwen2
11
  - trl
12
+ - sft
13
  ---
14
 
15
  # Uploaded model
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ehristoforu/Qwen2-1.5b-it-chat-sp-ru",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 1536,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000.0,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.44.0",
27
+ "unsloth_version": "2024.8",
28
+ "use_cache": true,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151936
31
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 32768,
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.1,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.44.0"
15
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c1a2a725d2276468d81248195f0dc92cb3604b90b6161ea7661d7db4b96b66
3
+ size 3087542290