Text Generation
memra
Safetensors
qwen3
speculative-decoding
dspark
dflash
draft-model
specforge
sglang
agentic
conversational
Eval Results (legacy)
Instructions to use tiyuvta/Qwen3.8-27B-DSpark-Agentic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- memra
How to use tiyuvta/Qwen3.8-27B-DSpark-Agentic with memra:
# memra serves NVIDIA Blackwell workstation and consumer cards (sm_120a), with a # compile-gated Hopper lane. Prebuilt binaries need Linux x86_64 and driver 580+, # and no CUDA toolkit. curl -fsSL https://raw.githubusercontent.com/avifenesh/memra/main/tools/install.sh | sh
# One chat-templated generation. In a repo with several GGUF files, append # :<substring> to choose one, for example hf:tiyuvta/Qwen3.8-27B-DSpark-Agentic:Q4_K_M MEMRA_CHAT=1 run-gen hf:tiyuvta/Qwen3.8-27B-DSpark-Agentic --prompt "Explain KV caches in one sentence."
# Or an OpenAI-compatible server on 127.0.0.1:8080. MEMRA_MODELS="model=hf:tiyuvta/Qwen3.8-27B-DSpark-Agentic" memra-server
- Notebooks
- Google Colab
- Kaggle
weights: DSpark drafter final checkpoint (62 tensors BF16, sha256 3c4e7d51f6a7...)
Browse files- model.safetensors +3 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c4e7d51f6a7492fd3c289e392424ab0fba31dc7b4ab4896da10a5eeb21fcd6f
|
| 3 |
+
size 2718576122
|