Clean model card for public release

README.md

@@ -1,6 +1,7 @@
 ---
 base_model: Jackrong/Qwopus3.6-27B-v2
 library_name: transformers
+pipeline_tag: text-generation
 tags:
   - qwen3.6
   - qwopus
@@ -10,17 +11,16 @@ tags:
   - vllm
   - int4
   - quantized
-license: other
+license: apache-2.0
 ---
 
 ![Qwopus3.6-27B-v2 GPTQ-Pro v1 RTX 3090 benchmark](assets/qwopus-gptq-pro-v1-rtx3090-benchmark.png)
 
-
 # Qwopus3.6-27B-v2 GPTQ-Pro v1
 
-This is the first public-ready GPTQ-Pro 4-bit release of `Jackrong/Qwopus3.6-27B-v2`, built to make this excellent Qwopus/Qwen3.6 model practical to run in vLLM with GPTQ-Marlin kernels and long-context inference.
+This is a GPTQ-Pro 4-bit quantization of `Jackrong/Qwopus3.6-27B-v2`, built to make this excellent Qwopus/Qwen3.6 model practical to run in vLLM with GPTQ-Marlin kernels and long-context inference.
 
-The goal is simple: preserve as much of the original model's character and capability as possible while making it efficient enough for real local/homelab serving, including RTX 3090-class deployments.
+The goal is simple: preserve as much of the original model's character and capability as possible while making it efficient enough for single-GPU RTX 3090-class vLLM deployments.
 
 This is not a new fine-tune. It is a quantized derivative of the original Qwopus3.6-27B-v2 model.
 
@@ -57,7 +57,9 @@ Thanks to Jackrong for the original Qwopus3.6 model, and to groxaxo for GPTQ-Pro
 | FOEM beta | `0.2` |
 | Batch size | `1` |
 
-Preserved modules include vision, `lm_head`, embeddings, norms, and MTP modules. Post-publication validation showed the internal `ns256-v2` artifact preserves MTP metadata but does **not** include actual `mtp.*` tensors in `model.safetensors.index.json`, so this release should be treated as non-MTP for vLLM speculative decoding.
+Preserved modules include vision, `lm_head`, embeddings, and norms.
+
+Validation showed that this artifact preserves MTP-related configuration metadata, but does **not** include actual `mtp.*` tensors in `model.safetensors.index.json`, so this release should be treated as non-MTP for vLLM speculative decoding.
 
 Post-save compatibility patch:
 
@@ -66,7 +68,7 @@ Post-save compatibility patch:
 
 ## Intended serving setup
 
-This checkpoint is intended for local/homelab vLLM serving on RTX 3090-class hardware.
+This checkpoint is intended for text-only vLLM serving on RTX 3090-class hardware.
 
 Recommended vLLM options:
 
@@ -92,7 +94,7 @@ vllm serve XReyRobert/Qwopus3.6-27B-v2-GPTQ-Pro-v1 \
 
 ## Reasoning / thinking mode
 
-This model preserves Qwen3-style reasoning behavior. The Hermes validation below was run with thinking enabled.
+This model preserves Qwen3-style reasoning behavior. The validation workload below was run with thinking enabled.
 
 ## MTP / speculative decoding status
 
@@ -108,16 +110,16 @@ That MTP-GPTQ artifact works and reaches good draft acceptance, but it was still
 
 ## RTX 3090 validation status
 
-This checkpoint was validated locally on an RTX 3090 24GB with vLLM, `max_model_len=131072`, `kv_cache_dtype=fp8_e5m2`, prefix caching enabled, and Hermes running with thinking enabled.
+This checkpoint was validated on an RTX 3090 24GB with vLLM, `max_model_len=131072`, `kv_cache_dtype=fp8_e5m2`, prefix caching enabled, and thinking enabled.
 
-Observed Hermes/vLLM workload metrics:
+Observed vLLM multi-turn agent workload metrics:
 
 | Metric | Observed value | Notes |
 |---|---:|---|
-| Requests observed | `15` | Hermes session calls |
+| Requests observed | `15` | Multi-turn agent session calls |
 | vLLM request success count | `15/15` | No vLLM errors observed during the sample |
-| Average prompt size | `33,172` tokens | Real multi-turn Hermes workload |
-| Average output size | `322` tokens | Real Hermes responses |
+| Average prompt size | `33,172` tokens | Real multi-turn workload |
+| Average output size | `322` tokens | Real generated responses |
 | Average time to first token | `5.70s` | Prometheus TTFT summary |
 | Average end-to-end request latency | `13.07s` | Includes prefill, decode, and serving overhead |
 | Average time per output token | `0.0230s/token` | vLLM TPOT summary |
@@ -127,7 +129,7 @@ Observed Hermes/vLLM workload metrics:
 | Live 60s generation throughput | about `19.1 generated tok/s` | Aggregate over full window, including prefill and idle mix |
 | Live 60s prefix-cache hit ratio | `78.9%` | Delta over the observed window |
 
-These are practical Hermes session metrics, not a synthetic benchmark. They are useful for RTX 3090-class homelab serving expectations, especially multi-turn long-context usage with prefix caching.
+These are practical multi-turn serving metrics, not a synthetic benchmark. They are useful for RTX 3090-class long-context serving expectations, especially multi-turn usage with prefix caching.
 
 ## Compatibility notes
 
@@ -138,7 +140,7 @@ This artifact was built and validated for text-only vLLM serving without specula
 - Experimental quantization.
 - MTP/speculative decoding is not supported by this published artifact because `mtp.*` tensors are missing.
 - Quality has not yet been benchmarked against the BF16 source model.
-- RTX 3090 metrics above are observed Hermes workload numbers, not a controlled benchmark suite.
+- RTX 3090 metrics above are observed workload numbers, not a controlled benchmark suite.
 - Use at your own risk, especially for long-context or tool-calling workflows.
 
 ## References
@@ -147,6 +149,6 @@ This artifact was built and validated for text-only vLLM serving without specula
 - GPTQ-Pro tooling: [groxaxo/GPTQ-Pro](https://github.com/groxaxo/GPTQ-Pro)
 - Reference GPTQ-Pro recipe: [groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit](https://huggingface.co/groxaxo/Qwen3.6-27B-GPTQ-Pro-4bit)
 
-## Personal project notice
+## Individual project notice
 
-This repository is a personal research project. The model, benchmarks, opinions, and documentation are my own and are not affiliated with, sponsored by, or endorsed by my employer or any organization I am associated with.
+This repository is an individual research project. It is not affiliated with, sponsored by, or endorsed by any employer or organization.