Downloads · 30 days
6
11% of all-time downloads
open-llama-3b-openthought-mid-lora
ping98k/open-llama-3b-openthought-mid-lora
open-llama-3b-openthought-mid-lora is a machine learning model from ping98k. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter for OpenLLaMA 3B v2, fine-tuned on OpenThoughts-114k (DeepSeek-R1 reasoning traces).
All-time downloads
55
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Apr 13, 2026
- Updated
- Apr 13, 2026
- SHA
- 6487fa01
Base models
Model card
From the Hugging Face model README
open-llama-3b-openthought-mid-lora
LoRA adapter for OpenLLaMA 3B v2, fine-tuned on OpenThoughts-114k (DeepSeek-R1 reasoning traces).
Training
- Base: open_llama_3b_v2 (4-bit NF4)
- Method: QLoRA (r=32, alpha=32)
- Data: open-thoughts/OpenThoughts-114k (filtered <= 2024 tokens, 10,582 samples)
- Epochs: 3
- Batch size: 128
- LR: 2e-4 (cosine, warmup 24 steps)
- Loss: full sequence (pad masked)
- Packing: greedy bin packing sorted by length
- Context: 2024 (native, no RoPE scaling)
- Special tokens: Qwen3.5 chat template
- modules_to_save: embed_tokens, lm_head
- Final loss: 0.71
Format
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
{question}<|im_end|>
<|im_start|>assistant
<think>
{reasoning}
</think>
{answer}<|im_end|>
Merged model
- Library
- peft
- Created
- Apr 13, 2026
- Updated
- Apr 13, 2026