Autotrain compatible Base model:finetune:jackfram/l... Base model:jackfram/llama-68m Conversational Dataset:amod/mental health cou... Dataset:cognitivecomputations/... Dataset:databricks/databricks-... Dataset:mlabonne/chatml dpo pa... Dataset:open-orca/openorca Dataset:sablo/oasst2 curated Dataset:starfishmedical/webgpt... Dataset:thudm/webglm-qa Dataset:totally-not-an-llm/eve... En Endpoints compatible Llama Model-index Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Felladrin/Llama-68M-Chat-v1
Llama 68M Chat V1 Benchmarks
ARC: 23.29 vs 96.7 (so35)-75.9%
HellaSwag: 28.27 vs 95.3 (gpt4)-70.3%
MMLU: 25.18 vs 88.3 (so35)-71.5%
TruthfulQA: 47.27 vs 59 (gpt4)-19.9%
WinoGrande: 54.3 vs 87.5 (gpt4)-37.9%
LLME Score: 0.22481
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)
Llama 68M Chat V1 Parameters and Internals
| Model Type |
|
| LLM Name | Llama 68M Chat V1 |
| Repository 🤗 | https://huggingface.co/Felladrin/Llama-68M-Chat-v1 |
| Base Model(s) | |
| Model Size | 68m |
| Required VRAM | 0.3 GB |
| Updated | 2025-02-22 |
| Maintainer | Felladrin |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 2048 |
| Model Max Length | 2048 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float32 |
Best Alternatives to Llama 68M Chat V1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 68M Fft | 4K / 0.1 GB | 312 | 0 |
| Llama 43M Beta | 2K / 0.2 GB | 229 | 0 |
| Llama 68M | 2K / 0 GB | 517565 | 26 |
| Vicuna 68M | 2K / 0.3 GB | 2732 | 3 |
| Gpt2 Sft Dutch | 2K / 0.1 GB | 20 | 0 |
| Llama 68M Oasst Top1 | 2K / 0.3 GB | 155 | 0 |
| Llama 68M Finetuned Wikitext2 | 2K / 0.3 GB | 164 | 0 |
| Llama 68M Oasst | 2K / 0.3 GB | 93 | 0 |
| Jack 68M Text Structurization | 2K / 0.1 GB | 10 | 2 |
| JackFram Llama 68M | 2K / 0.3 GB | 119 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than Felladrin/Llama-68M-Chat-v1 .
Rank the Llama 68M Chat V1 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