4-bit Adapter Base model:adapter:ai21labs/ja... Base model:ai21labs/jamba-v0.1 Bitsandbytes Custom code Finetuned Generated from trainer Jamba Lora Peft Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlabonne/Jambalpaca-v0.1
Jambalpaca V0.1 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)
Jambalpaca V0.1 Parameters and Internals
| Training Details |
|
| LLM Name | Jambalpaca V0.1 |
| Repository 🤗 | https://huggingface.co/mlabonne/Jambalpaca-v0.1 |
| Base Model(s) | |
| Model Size | 51.6b |
| Required VRAM | 103.4 GB |
| Updated | 2025-03-14 |
| Maintainer | mlabonne |
| Model Files | |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | dt_proj|router|v_proj|k_proj|gate_proj|o_proj|in_proj|out_proj|up_proj|down_proj|q_proj|x_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0.05 |
| R Param | 32 |
Rank the Jambalpaca V0.1 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? 45019 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227