izaznov commited on
Commit
16cd834
·
verified ·
1 Parent(s): da6ad3b

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Qwen2.5-14B-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": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 151665,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "float16",
22
+ "bnb_4bit_quant_type": "nf4",
23
+ "bnb_4bit_use_double_quant": true,
24
+ "llm_int8_enable_fp32_cpu_offload": false,
25
+ "llm_int8_has_fp16_weight": false,
26
+ "llm_int8_skip_modules": null,
27
+ "llm_int8_threshold": 6.0,
28
+ "load_in_4bit": true,
29
+ "load_in_8bit": false,
30
+ "quant_method": "bitsandbytes"
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": null,
34
+ "rope_theta": 1000000.0,
35
+ "sliding_window": null,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.46.2",
39
+ "unsloth_version": "2024.11.7",
40
+ "use_cache": true,
41
+ "use_sliding_window": false,
42
+ "vocab_size": 152064
43
+ }
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": 151665,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.46.2"
15
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e1b8b08ddbd676d7edd657588fe15f5778ca3078874104cc8b3b90ba9849ca
3
+ size 4998550163
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c8d5787a01eb66d8394414913d423755c26f36b7ee6421fc5104ef0a47fdb0
3
+ size 4933608616
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff