4-bit 4bit Autotrain compatible Base model:quantized:theros/qw... Base model:theros/qwen2.5-cold... Bitsandbytes Conversational En Endpoints compatible Grpo Lora Quantized Qwen2 Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/SvalTek/ColdBrew-600_4bit
ColdBrew 600 4bit 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)
ColdBrew 600 4bit Parameters and Internals
| LLM Name | ColdBrew 600 4bit |
| Repository 🤗 | https://huggingface.co/SvalTek/ColdBrew-600_4bit |
| Base Model(s) | |
| Model Size | 4.5b |
| Required VRAM | 5.6 GB |
| Updated | 2025-07-10 |
| Maintainer | SvalTek |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|k_proj|down_proj|o_proj|v_proj|q_proj|gate_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Rank the ColdBrew 600 4bit 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? 50035 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124