krishna195 commited on
Commit
1a6fd03
·
verified ·
1 Parent(s): 4e0a01c

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - llama
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - llama
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 100257,
9
+ "eos_token_id": 100265,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 17920,
15
+ "max_position_embeddings": 16384,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 40,
19
+ "num_hidden_layers": 40,
20
+ "num_key_value_heads": 10,
21
+ "original_max_position_embeddings": 16384,
22
+ "pad_token_id": 100351,
23
+ "pretraining_tp": 1,
24
+ "quantization_config": {
25
+ "bnb_4bit_compute_dtype": "float16",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": true,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rms_norm_eps": 1e-05,
37
+ "rope_scaling": null,
38
+ "rope_theta": 250000,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "float16",
41
+ "transformers_version": "4.49.0",
42
+ "unsloth_fixed": true,
43
+ "unsloth_version": "2025.3.18",
44
+ "use_cache": true,
45
+ "vocab_size": 100352
46
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100265,
5
+ "max_length": 16384,
6
+ "pad_token_id": 100351,
7
+ "transformers_version": "4.49.0"
8
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b425c286aae58f8eb5b98812dec3398b80c0738404f4c13ce88ab6424a476e
3
+ size 4971805365
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5de548137f9ed441775c12f314929e3cd827047a867d99da4898f44af6a892da
3
+ size 4392572525
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57010d961bd3e9561280b0d17a44cee4e190362cbf21cd51c5c331c92c778cb7
3
+ size 1027604608
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff