dolphin-2.9.2-qwen2-7b:Q3_K_M
Upstream reference: Dolphin 2.9.2 Qwen2 7B
Publisher: Dolphin / Eric Hartford and collaborators
The publishers describe a full-weight instruction fine-tune of Qwen2-7B using conversational, coding and function-call data.
Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.
Published upstream specifications
- Base lineage
- Qwen2-7B Source
- Documented fine-tuning sequence length
- 16K tokens, publisher notation Source
- Documented prompt format
- ChatML Source
Publisher-described uses
- Instruction-following conversation, coding and application function calls. Source
Reference limitations
- The card’s Apache-2.0 metadata conflicts with its narrative Tongyi Qianwen license statements; no simplified license label is assigned. The base model’s 128K figure is distinct from the fine-tuning sequence length. Quantization tags do not verify a converted digest. Source
A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.
Publisher sources
- Dolphin 2.9.2 Qwen2 7B official documentation — Dolphin / Eric Hartford and collaborators. Checked .
Links
Recorded references do not establish downloadable weights, licensing or current availability.
7.0B
parameters
131072
context
Where dolphin-2.9.2-qwen2-7b:Q3_K_M comes from
Company / lab
Cognitive Computations
See every model and family from this maker.
Model family
dolphin-2.9.2-qwen2-7b
Other versions and sizes in this line.