4-bit 4bit Autotrain compatible Base model:quantized:unsloth/o... Base model:unsloth/openhermes-... Bitsandbytes Conversational En Endpoints compatible Mistral Quantized Region:us Safetensors Sft Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/kheopss/kheops_fr_en_epoch1_4bit_v4
Kheops Fr En Epoch1 4bit V4 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)
Kheops Fr En Epoch1 4bit V4 Parameters and Internals
| LLM Name | Kheops Fr En Epoch1 4bit V4 |
| Repository 🤗 | https://huggingface.co/kheopss/kheops_fr_en_epoch1_4bit_v4 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.1 GB |
| Updated | 2024-08-08 |
| Maintainer | kheopss |
| Model Type | mistral |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.41.1 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32002 |
| Torch Data Type | bfloat16 |
Best Alternatives to Kheops Fr En Epoch1 4bit V4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...al Nemo Instruct 2407 Bnb 4bit | 1000K / 8.3 GB | 18854 | 27 |
| ...istral Nemo Base 2407 Bnb 4bit | 1000K / 8.3 GB | 9876 | 15 |
| ...t 3.5 0106 128K 4.0bpw H6 EXL2 | 128K / 3.9 GB | 8 | 1 |
| ...t 3.5 0106 128K 8.0bpw H8 EXL2 | 128K / 7.4 GB | 7 | 1 |
| ...tral 7B Instruct V0.3 Bnb 4bit | 32K / 4.1 GB | 158505 | 21 |
| Mistral 7B V0.3 Bnb 4bit | 32K / 4.1 GB | 20582 | 15 |
| Mistral 7B Instruct V0.2 Fp16 | 32K / 14.4 GB | 26 | 0 |
| Mistral 7B Instruct V0.2 4bit | 32K / 4.3 GB | 270 | 1 |
| ...tral 7B Instruct V0.2 Bnb 4bit | 32K / 4.1 GB | 14005 | 32 |
| MistralContinuedFine | 32K / 14.5 GB | 1447 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than kheopss/kheops_fr_en_epoch1_4bit_v4 .
Rank the Kheops Fr En Epoch1 4bit V4 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