4-bit Axolotl Base model:adapter:model Bitsandbytes Conversational Dataset:hardlyworking/hardlyrp... Endpoints compatible Lora Mistral Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/hardlyworking/MS32-2
MS32 2 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
MS32 2 Parameters and Internals
| LLM Name | MS32 2 |
| Repository 🤗 | https://huggingface.co/hardlyworking/MS32-2 |
| Base Model(s) | |
| Required VRAM | 0.7 GB |
| Updated | 2025-08-16 |
| Maintainer | hardlyworking |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizerFast |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|gate_proj|q_proj|o_proj|k_proj|v_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to MS32 2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Asdf | 0K / 0.2 GB | 67 | 0 |
| MS32 3 | 0K / 1.5 GB | 18 | 0 |
| Tinyllama Cpt | 0K / 0.5 GB | 6 | 0 |
| Fine Tune Sentimental Llama | 0K / 0 GB | 6 | 0 |
| VLM2Vec LoRA | 0K / 0 GB | 44 | 10 |
| QuietStar Project | 0K / GB | 7 | 2 |
| Finetuned Llava Lora | 0K / 0.1 GB | 5 | 0 |
| Alphace Email | 0K / 0.1 GB | 5 | 0 |
| Qwen7B Haiguitang | 0K / 15.3 GB | 5 | 0 |
| Modelv3 | 0K / 13.5 GB | 5 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than hardlyworking/MS32-2 .
Rank the MS32 2 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 50705 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124