Autotrain compatible Conversational Endpoints compatible F16 Ggml Gguf Mistral Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/boricua/merlinite-7b-ocp4.15-v0.3
Merlinite 7B Ocp4.15 V0.3 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)
Merlinite 7B Ocp4.15 V0.3 Parameters and Internals
| LLM Name | Merlinite 7B Ocp4.15 V0.3 |
| Repository 🤗 | https://huggingface.co/boricua/merlinite-7b-ocp4.15-v0.3 |
| Model Size | 7b |
| Required VRAM | 14.5 GB |
| Updated | 2025-02-22 |
| Maintainer | boricua |
| Model Type | mistral |
| Model Files | |
| GGML Quantization | Yes |
| GGUF Quantization | Yes |
| Quantization Type | ggml|gguf |
| Model Architecture | MistralForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.38.2 |
| Padding Token | <|pad|> |
| Vocabulary Size | 32008 |
| Torch Data Type | bfloat16 |
Best Alternatives to Merlinite 7B Ocp4.15 V0.3
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Mistrilitary 7B | 32K / 7.7 GB | 128 | 19 |
| Mistral Scary Story Finetune | 32K / 14.5 GB | 30 | 0 |
| Mistral 7B V0.2 Csn SFT | 32K / 14.4 GB | 15 | 0 |
| AzzurroQuantized | 32K / 4.4 GB | 333 | 4 |
| Instruct 16bit | 32K / 0.4 GB | 5 | 0 |
| Shiftdocs 7B Ocp4.15 V0.3 | 32K / 14.5 GB | 11 | 0 |
| AzzurroQuantized | 32K / 4.4 GB | 222 | 4 |
| Merlinite 7B Ocp4.15 V0.1 | 32K / 4.4 GB | 12 | 0 |
| Filiberto 7B Instruct Exp1 | 32K / 14.5 GB | 31 | 0 |
| MistralMusic | 32K / 14.4 GB | 26 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than boricua/merlinite-7b-ocp4.15-v0.3 .
Rank the Merlinite 7B Ocp4.15 V0.3 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