Arxiv:2302.13971 Autotrain compatible Conversational Endpoints compatible Gguf Llama Lora Q4 Quantized Region:us Safetensors Sft Sharded Tensorboard Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/us4/fin-llama3.1-8b
Fin Llama3.1 8B 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)
Fin Llama3.1 8B Parameters and Internals
| LLM Name | Fin Llama3.1 8B |
| Repository 🤗 | https://huggingface.co/us4/fin-llama3.1-8b |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-03-13 |
| Maintainer | us4 |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | q4|gguf|q4_k|q5_k |
| Model Architecture | AutoModelForCausalLM |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|v_proj|o_proj|q_proj|down_proj|k_proj|up_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0 |
| R Param | 128 |
Best Alternatives to Fin Llama3.1 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ReWiz Llama 3.1 8B V2 | 0K / 16.1 GB | 613 | 1 |
| TalktoaiZERO | 0K / 16.1 GB | 250 | 5 |
| Llama 3 8B Chat Me | 0K / 16.1 GB | 325 | 0 |
| Llama3 Credpol | 0K / 21.9 GB | 81 | 0 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 8 | 0 |
| Genesist 8B EarlyPrototype 0.3 | 0K / 16.1 GB | 86 | 0 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 11 | 0 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 28 | 0 |
| Fine Tuning Bebidas | 0K / 16.1 GB | 26 | 0 |
| Llm Nl To Cmd | 0K / 16.1 GB | 12 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than us4/fin-llama3.1-8b .
Rank the Fin Llama3.1 8B 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? 45005 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227