Downloads · 30 days
6
25% of all-time downloads
stark-mistral-7b
beratcmn/stark-mistral-7b
stark-mistral-7b is a machine learning model from beratcmn. 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.
This was a funny saturday evening experiment where I trained Mistral 7B with total of 148 quotes from Tony Stark in Iron Man 1 and Iron Man 2. There is a lot to do but this was a simple test.
All-time downloads
24
Public
Parameters
7.2B
14.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 99%
At a glance
- Library
- peft
- Model type
- mistral
- Access
- Public
- Created
- Oct 28, 2023
- Updated
- Nov 3, 2023
- SHA
- 5b3fd2e6
Model card
From the Hugging Face model README
About
This was a funny saturday evening experiment where I trained Mistral 7B with total of 148 quotes from Tony Stark in Iron Man 1 and Iron Man 2. There is a lot to do but this was a simple test.
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.5.0
- Library
- peft
- Type
- mistral
- Created
- Oct 28, 2023
- Updated
- Nov 3, 2023