Piyu12 commited on
Commit
1d52dce
·
verified ·
1 Parent(s): d115813

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show
  1. adapter_config.json +10 -6
  2. adapter_model.safetensors +2 -2
adapter_config.json CHANGED
@@ -1,13 +1,16 @@
1
  {
 
2
  "alpha_pattern": {},
 
3
  "auto_mapping": {
4
- "base_model_class": "Qwen3VLForConditionalGeneration",
5
- "parent_library": "transformers.models.qwen3_vl.modeling_qwen3_vl",
6
  "unsloth_fixed": true
7
  },
8
- "base_model_name_or_path": "unsloth/qwen3-vl-8b-instruct-unsloth-bnb-4bit",
9
  "bias": "none",
10
  "corda_config": null,
 
11
  "eva_config": null,
12
  "exclude_modules": null,
13
  "fan_in_fan_out": false,
@@ -17,18 +20,19 @@
17
  "layers_pattern": null,
18
  "layers_to_transform": null,
19
  "loftq_config": {},
20
- "lora_alpha": 16,
21
  "lora_bias": false,
22
  "lora_dropout": 0,
23
  "megatron_config": null,
24
  "megatron_core": "megatron.core",
25
  "modules_to_save": null,
26
  "peft_type": "LORA",
 
27
  "qalora_group_size": 16,
28
- "r": 16,
29
  "rank_pattern": {},
30
  "revision": null,
31
- "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:qkv|proj|linear_fc1|linear_fc2|q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
32
  "target_parameters": null,
33
  "task_type": "CAUSAL_LM",
34
  "trainable_token_indices": null,
 
1
  {
2
+ "alora_invocation_tokens": null,
3
  "alpha_pattern": {},
4
+ "arrow_config": null,
5
  "auto_mapping": {
6
+ "base_model_class": "Mistral3ForConditionalGeneration",
7
+ "parent_library": "transformers.models.mistral3.modeling_mistral3",
8
  "unsloth_fixed": true
9
  },
10
+ "base_model_name_or_path": "unsloth/Ministral-3-3B-Instruct-2512",
11
  "bias": "none",
12
  "corda_config": null,
13
+ "ensure_weight_tying": false,
14
  "eva_config": null,
15
  "exclude_modules": null,
16
  "fan_in_fan_out": false,
 
20
  "layers_pattern": null,
21
  "layers_to_transform": null,
22
  "loftq_config": {},
23
+ "lora_alpha": 32,
24
  "lora_bias": false,
25
  "lora_dropout": 0,
26
  "megatron_config": null,
27
  "megatron_core": "megatron.core",
28
  "modules_to_save": null,
29
  "peft_type": "LORA",
30
+ "peft_version": "0.18.0",
31
  "qalora_group_size": 16,
32
+ "r": 32,
33
  "rank_pattern": {},
34
  "revision": null,
35
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:gate_proj|up_proj|down_proj|k_proj|v_proj|q_proj|o_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:gate_proj|up_proj|down_proj|k_proj|v_proj|q_proj|o_proj)))",
36
  "target_parameters": null,
37
  "task_type": "CAUSAL_LM",
38
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ebc8e7f0ebbb4b96d07491f6c2e99dcb0ce26632cbabf92f9a51d8c2718723d
3
- size 205492968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540cabd278419a0633ea5598b9e261ee394d4db3f7989b1dda1f3f146514191a
3
+ size 270117632