| Model Type |
|
| LLM Name | Valkyrie V1 GPTQ |
| Repository ๐ค | https://huggingface.co/TheBloke/Valkyrie-V1-GPTQ |
| Model Name | Valkyrie v1 |
| Model Creator | John Smith |
| Base Model(s) | |
| Model Size | 7.2b |
| Required VRAM | 4.2 GB |
| Updated | 2025-12-23 |
| Maintainer | TheBloke |
| Model Type | mistral |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | MistralForCausalLM |
| License | apache-2.0 |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.35.2 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| HamSter 0.1 GPTQ | 32K / 4.2 GB | 33 | 2 |
| Quantum V0.01 GPTQ | 32K / 4.2 GB | 26 | 2 |
| Metis 0.3 GPTQ | 32K / 4.2 GB | 19 | 1 |
| Metis 0.1 GPTQ | 32K / 4.2 GB | 16 | 1 |
| ....5 Neural Chat V3.3 Slerp GPTQ | 32K / 4.2 GB | 12 | 3 |
| ...Sft Bnb 4bit DPO Mtbr 180steps | 32K / 14.4 GB | 5 | 0 |
| ...Sft Bnb 4bit DPO Mtbc 213steps | 32K / 14.4 GB | 5 | 0 |
| ...Sft Bnb 4bit DPO Mtbo 180steps | 32K / 14.4 GB | 9 | 0 |
| Mixtral V0.3 Full 16bit V2 | 32K / 14.5 GB | 5 | 0 |
| ...88 07.02 RP DPO Merged 16bit 3 | 32K / 14.4 GB | 10 | 0 |
๐ 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! ๐