Merged Model Arxiv:1910.09700 8-bit Autotrain compatible Bitsandbytes Conversational Endpoints compatible Gemma Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/chansung/mental_health_counseling_v0.1_merged
Mental Health Counseling V0.1 Merged 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)
Mental Health Counseling V0.1 Merged Parameters and Internals
| LLM Name | Mental Health Counseling V0.1 Merged |
| Repository 🤗 | https://huggingface.co/chansung/mental_health_counseling_v0.1_merged |
| Merged Model | Yes |
| Model Size | 8.5b |
| Required VRAM | 9.4 GB |
| Updated | 2025-09-23 |
| Maintainer | chansung |
| Model Type | gemma |
| Model Files | |
| Model Architecture | GemmaForCausalLM |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 256000 |
| Torch Data Type | float16 |
Best Alternatives to Mental Health Counseling V0.1 Merged
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| FiLLM3 NER | 8K / 17.1 GB | 24 | 0 |
| FiLLM Experimental | 8K / 17.1 GB | 20 | 0 |
| Openchat 3.5 0106 Gemma | 8K / 17.1 GB | 2464 | 58 |
| Gemma ChemWiz Rdkit 16bit | 8K / 17.1 GB | 3 | 1 |
| Gemma ChemWiz 16bit | 8K / 17.1 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than chansung/mental_health_counseling_v0.1_merged .
Rank the Mental Health Counseling V0.1 Merged 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124