4bit Autotrain compatible En Endpoints compatible Ext 8k Lora Quantized Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/mikun/Qwen2.5-8k-sports
Qwen2.5 8K Sports 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)
Qwen2.5 8K Sports Parameters and Internals
| LLM Name | Qwen2.5 8K Sports |
| Repository 🤗 | https://huggingface.co/mikun/Qwen2.5-8k-sports |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2024-12-04 |
| Maintainer | mikun |
| Model Files | |
| Supported Languages | en |
| Context Length | 8k |
| 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 | v_proj|gate_proj|k_proj|q_proj|down_proj|up_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
| Errors | replace |
Best Alternatives to Qwen2.5 8K Sports
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| WorldBuilder 7B | 0K / 14.5 GB | 10 | 0 |
| Unsloth Alpaca | 0K / 14.5 GB | 5 | 0 |
| ... WAEMU Africa Banking Analysis | 0K / 15.2 GB | 6 | 1 |
| Mistralbasket1 | 0K / 0.2 GB | 45 | 0 |
| Gemma 7B Bnb 4bit | 0K / 17.1 GB | 5 | 0 |
| Mistral 7B V0.3 | 0K / 14.5 GB | 7 | 0 |
| Refined Llama3 | 0K / 0.2 GB | 6 | 0 |
| Gemma Unsloth Alpaca | 0K / 17.1 GB | 7 | 2 |
| Mistral 7B Instruct 4bit | 0K / 0.2 GB | 8 | 1 |
| Qwen 2 Healthcare Checkpoint 1 | 0K / 15.2 GB | 0 | 0 |
Rank the Qwen2.5 8K Sports 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227