Merged Model 4bit Autotrain compatible Conversational Dataset:uncovai/fineweb cc-mai... En Endpoints compatible Instruct Mistral Phi3 Pytorch Quantized Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/FlofloB/test_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit
Test Continued Pretraining Phi 3 Mini 4K Instruct Unsloth Merged 16bit Benchmarks
MMLU Pro: 30.23
GPQA: 8.17
MUSR: 12.45
BBH: 32.88
IFEval: 52.15 vs 88 (so35)-40.7%
MATH Lvl 5: 10.88
LLME Score: 0.30311
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)
Test Continued Pretraining Phi 3 Mini 4K Instruct Unsloth Merged 16bit Parameters and Internals
| LLM Name | Test Continued Pretraining Phi 3 Mini 4K Instruct Unsloth Merged 16bit |
| Repository 🤗 | https://huggingface.co/FlofloB/test_continued_pretraining_Phi-3-mini-4k-instruct_Unsloth_merged_16bit |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 3.8b |
| Required VRAM | 7.6 GB |
| Updated | 2025-02-15 |
| Maintainer | FlofloB |
| Model Type | mistral |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.46.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|placeholder6|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Test Continued Pretraining Phi 3 Mini 4K Instruct Unsloth Merged 16bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Word Problems 200K Model 16bit | 4K / 7.6 GB | 3879 | 0 |
| Porpoise1 | 4K / 7.6 GB | 374 | 0 |
| Pii Redaction V0.3 | 4K / 7.6 GB | 161 | 2 |
| ...rser User V9b Epoch 7 Lr 0.002 | 4K / 7.6 GB | 80 | 0 |
| ...100 Percent Low Med Perplexity | 4K / 7.6 GB | 83 | 0 |
| ...22 Epoch7 0.002 Nosystemprompt | 4K / 7.6 GB | 82 | 0 |
| ...ch6 0.002 V6 Systempromt Short | 4K / 7.6 GB | 80 | 0 |
| Ymail Search Phi3 Vllm Model | 4K / 7.6 GB | 82 | 0 |
| ... 4K Instruct Matter 0.1 Slim A | 4K / 7.6 GB | 16 | 2 |
| ... Af 100 Percent Low Bt Rouge 1 | 4K / 7.6 GB | 83 | 0 |
Rank the Test Continued Pretraining Phi 3 Mini 4K Instruct Unsloth Merged 16bit 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? 43137 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227