pashaprokaz commited on
Commit
20d6d39
1 Parent(s): 8e8f511

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - qwen2
10
  - trl
 
11
  base_model: unsloth/Qwen2-7B-Instruct-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - qwen2
10
  - trl
11
+ - sft
12
  base_model: unsloth/Qwen2-7B-Instruct-bnb-4bit
13
  ---
14
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Qwen2-7B-Instruct-bnb-4bit",
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": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
19
+ "quantization_config": {
20
+ "bnb_4bit_compute_dtype": "float16",
21
+ "bnb_4bit_quant_type": "nf4",
22
+ "bnb_4bit_use_double_quant": true,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": true,
28
+ "load_in_8bit": false,
29
+ "quant_method": "bitsandbytes"
30
+ },
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_theta": 1000000.0,
33
+ "sliding_window": 131072,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.41.2",
37
+ "unsloth_version": "2024.6",
38
+ "use_cache": true,
39
+ "use_sliding_window": false,
40
+ "vocab_size": 152064
41
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.41.2"
14
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a6fb1a22830a108db345a3d6b6ed150626c3299d9c71b806058be5aeaed644b
3
+ size 4457259455
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b6eef54ae6fe69f5715367e066a3f8a1c6d233fed8feb5bb358bf107d54660
3
+ size 1089994880
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff