nativeanish commited on
Commit
c3104db
·
verified ·
1 Parent(s): 3be99fa

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

README.md CHANGED
@@ -6,6 +6,7 @@ tags:
6
  - unsloth
7
  - mistral
8
  - trl
 
9
  license: apache-2.0
10
  language:
11
  - en
 
6
  - unsloth
7
  - mistral
8
  - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Mistral-Small-24B-Instruct-2501-unsloth-bnb-4bit",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 32768,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 11,
20
+ "quantization_config": {
21
+ "bnb_4bit_compute_dtype": "bfloat16",
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-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 100000000.0,
35
+ "sliding_window": null,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.49.0",
39
+ "unsloth_fixed": true,
40
+ "unsloth_version": "2025.2.15",
41
+ "use_cache": true,
42
+ "vocab_size": 131072
43
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "max_length": 32768,
7
+ "pad_token_id": 11,
8
+ "temperature": 0.15,
9
+ "transformers_version": "4.49.0"
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b333811b538d24ad2f9a8ec0abca0130445c75215e9ca1c5129dca9b3624f9
3
+ size 4983477376
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e115a028fc08b62614e7eb21dd7350b22901fd05d790860dca6ee2118036ad
3
+ size 4960899358
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee4f4d911553a90380b55b8dee52ca0831504e3099216621f4b4e9318cf5c83
3
+ size 4956026345
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff