volfan6415 commited on
Commit
0a5ee4a
·
verified ·
1 Parent(s): 0c91eed

📦 Add model, tokenizer, and model card

Browse files
README.md CHANGED
@@ -3,10 +3,10 @@ tags:
3
  - finetuned
4
  ---
5
 
6
- # meta-llama/Llama-3.1-8B-finetuned with Atomic
7
 
8
  ## Model Description
9
- This model was fine-tuned from `meta-llama/Llama-3.1-8B` on `fka/awesome-chatgpt-prompts` data using NOLA AI’s Atomic system.
10
 
11
  ## Training Data
12
  - **Dataset name:** fka/awesome-chatgpt-prompts
@@ -17,5 +17,6 @@ This model was fine-tuned from `meta-llama/Llama-3.1-8B` on `fka/awesome-chatgpt
17
  - **Used ATOMIC Speed:** True
18
 
19
  ## Final Metrics
20
- - **Training loss:** N/A
 
21
  ---
 
3
  - finetuned
4
  ---
5
 
6
+ # meta-llama/Llama-3.2-1B-finetuned with Atomic
7
 
8
  ## Model Description
9
+ This model was fine-tuned from `meta-llama/Llama-3.2-1B` on `fka/awesome-chatgpt-prompts` data using NOLA AI’s Atomic system.
10
 
11
  ## Training Data
12
  - **Dataset name:** fka/awesome-chatgpt-prompts
 
17
  - **Used ATOMIC Speed:** True
18
 
19
  ## Final Metrics
20
+ - **Training loss:** 1.5815104802449544
21
+ - **Training Runtime:** 0:00:46
22
  ---
adapter_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "base_model_class": "LlamaForCausalLM",
5
  "parent_library": "transformers.models.llama.modeling_llama"
6
  },
7
- "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
8
  "bias": "none",
9
  "corda_config": null,
10
  "eva_config": null,
@@ -27,12 +27,12 @@
27
  "rank_pattern": {},
28
  "revision": null,
29
  "target_modules": [
 
30
  "v_proj",
31
  "gate_proj",
 
32
  "k_proj",
33
  "q_proj",
34
- "o_proj",
35
- "down_proj",
36
  "up_proj"
37
  ],
38
  "task_type": null,
 
4
  "base_model_class": "LlamaForCausalLM",
5
  "parent_library": "transformers.models.llama.modeling_llama"
6
  },
7
+ "base_model_name_or_path": "meta-llama/Llama-3.2-1B",
8
  "bias": "none",
9
  "corda_config": null,
10
  "eva_config": null,
 
27
  "rank_pattern": {},
28
  "revision": null,
29
  "target_modules": [
30
+ "o_proj",
31
  "v_proj",
32
  "gate_proj",
33
+ "down_proj",
34
  "k_proj",
35
  "q_proj",
 
 
36
  "up_proj"
37
  ],
38
  "task_type": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36020e044dac18e4b1f3bc2bdd39e6a8f3a064be8bf47fdbfbee608db5afb45f
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9cd83605777c79ba8bcea5eecf6b31323bb85d686823f9d1199355175168d7
3
+ size 45118424
lorax_manifest.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "schema": "atomizer/lorax-manifest@v1",
3
- "created_at": "2025-09-10T14:49:06.688825+00:00",
4
  "artifacts": {
5
  "base_model_id": "",
6
  "adapters_repo_id": "volfan6415/DemoDayModel_LoRA",
@@ -14,7 +14,7 @@
14
  "adapter_source": "hub",
15
  "private": true
16
  },
17
- "runid": "a3c40e0c-ab71-43c1-9e2b-3c12e7647c93",
18
  "output_dir": "DemoDayModel",
19
  "training_args": {
20
  "bf16": true,
@@ -24,7 +24,7 @@
24
  "logging_steps": 10,
25
  "lr_scheduler_type": "linear",
26
  "max_grad_norm": 1,
27
- "num_train_epochs": 3,
28
  "optim": "adamw_torch_fused",
29
  "output_dir": "DemoDayModel",
30
  "per_device_eval_batch_size": 16,
 
1
  {
2
  "schema": "atomizer/lorax-manifest@v1",
3
+ "created_at": "2025-09-18T17:43:05.756765+00:00",
4
  "artifacts": {
5
  "base_model_id": "",
6
  "adapters_repo_id": "volfan6415/DemoDayModel_LoRA",
 
14
  "adapter_source": "hub",
15
  "private": true
16
  },
17
+ "runid": "eff98df7-f8ad-4385-bb48-20b20626c6da",
18
  "output_dir": "DemoDayModel",
19
  "training_args": {
20
  "bf16": true,
 
24
  "logging_steps": 10,
25
  "lr_scheduler_type": "linear",
26
  "max_grad_norm": 1,
27
+ "num_train_epochs": 10,
28
  "optim": "adamw_torch_fused",
29
  "output_dir": "DemoDayModel",
30
  "per_device_eval_batch_size": 16,