finnbusse commited on
Commit
daa6ff9
1 Parent(s): ba6006e

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -9,6 +9,8 @@ pipeline_tag: text-generation
9
  tags:
10
  - Detmold
11
  - unsloth
 
 
12
  emoji: 🧠
13
  ---
14
 
 
9
  tags:
10
  - Detmold
11
  - unsloth
12
+ - trl
13
+ - sft
14
  emoji: 🧠
15
  ---
16
 
config.json CHANGED
@@ -1,3 +1,48 @@
1
  {
2
- "model_type": "gemma2"
3
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "unsloth/gemma-2-9b-bnb-4bit",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 42,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 0,
25
+ "quantization_config": {
26
+ "bnb_4bit_compute_dtype": "float16",
27
+ "bnb_4bit_quant_type": "nf4",
28
+ "bnb_4bit_use_double_quant": true,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": true,
34
+ "load_in_8bit": false,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "query_pre_attn_scalar": 256,
38
+ "rms_norm_eps": 1e-06,
39
+ "rope_scaling": null,
40
+ "rope_theta": 10000.0,
41
+ "sliding_window": 4096,
42
+ "sliding_window_size": 4096,
43
+ "torch_dtype": "float16",
44
+ "transformers_version": "4.44.2",
45
+ "unsloth_version": "2024.9.post4",
46
+ "use_cache": true,
47
+ "vocab_size": 256000
48
+ }
generation_config.json CHANGED
@@ -3,6 +3,7 @@
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
5
  "eos_token_id": 1,
 
6
  "pad_token_id": 0,
7
- "transformers_version": "4.42.4"
8
  }
 
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
5
  "eos_token_id": 1,
6
+ "max_length": 8192,
7
  "pad_token_id": 0,
8
+ "transformers_version": "4.44.2"
9
  }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be7b9c7864e666fc4257882fdc8d7cb8f704bd478372465bdcd0cd85b40c4575
3
+ size 4979448150
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94dabf16015739bac9070e854ebb8e51b4ed0f1f83f6fca95d80c23637be74ef
3
+ size 1151731109
pytorch_model.bin.index.json CHANGED
The diff for this file is too large to render. See raw diff