rohit103 commited on
Commit
fb866c7
·
verified ·
1 Parent(s): e1c4179

Upload Qwen3ForCausalLM

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "google/gemma-2b",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
@@ -20,17 +20,17 @@
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
23
- "r": 64,
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
27
- "q_proj",
28
- "gate_proj",
29
  "o_proj",
 
 
30
  "down_proj",
 
31
  "v_proj",
32
- "k_proj",
33
- "up_proj"
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen3-0.6B-Base",
5
  "bias": "none",
6
  "corda_config": null,
7
  "eva_config": null,
 
20
  "megatron_core": "megatron.core",
21
  "modules_to_save": null,
22
  "peft_type": "LORA",
23
+ "r": 32,
24
  "rank_pattern": {},
25
  "revision": null,
26
  "target_modules": [
 
 
27
  "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
  "down_proj",
31
+ "gate_proj",
32
  "v_proj",
33
+ "k_proj"
 
34
  ],
35
  "task_type": "CAUSAL_LM",
36
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d1ef08cfd6d18e9b7fedacd53e160800fdd8b62329fd022b09b31f0c7cfc415
3
- size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065804fbc15076170bbcc0f1262acdfca6e7d4731a64350b3b64420415f44f8e
3
+ size 80792456
generation_config.json CHANGED
@@ -1,7 +1,6 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 2,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.52.3"
7
  }
 
1
  {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.57.1"
 
6
  }