commit 5b8a25a4d7250a625cea0b836e717b5ef98b6647 Author: ModelHub XC Date: Wed May 6 07:58:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ryancook/chromadb-context-1-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..575f1cc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,63 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-bf16.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-BF16.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-F16.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +chromadb-context-1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ba14c2 --- /dev/null +++ b/README.md @@ -0,0 +1,112 @@ +--- +license: apache-2.0 +library_name: gguf +base_model: + - chromadb/context-1 +pipeline_tag: text-generation +language: en +tags: + - gguf + - llama.cpp + - gpt-oss + - chromadb + - chroma + - moe + - text-generation + - quantized +--- + +# Chroma Context-1 — GGUF (llama.cpp) + +**GGUF weights for [Chroma Context-1](https://huggingface.co/chromadb/context-1),** converted for **[llama.cpp](https://github.com/ggml-org/llama.cpp)** and any runtime that loads GGUF (LM Studio, Ollama with compatible import paths, local servers, etc.). + +This repository exists because **the upstream model is distributed in PyTorch / safetensors form only**. These files are the same weights in **GGUF**, with a range of **llama-quantize** presets so you can trade quality for VRAM and disk. + +--- + +## Upstream (source of truth) + +| | Link | +|---|------| +| **Original weights & model card** | [**`chromadb/context-1`**](https://huggingface.co/chromadb/context-1) | +| **Architecture family** | gpt-oss MoE (see upstream card; base traceable to OpenAI **[`gpt-oss-20b`](https://huggingface.co/openai/gpt-oss-20b)**) | +| **License** | **Apache 2.0** (unchanged; you must comply with upstream terms) | + +**Attribution:** All tensors are derived from **[chromadb/context-1](https://huggingface.co/chromadb/context-1)**. This repo is a **community conversion** and is **not** affiliated with or endorsed by Chroma. For behavior, safety, and intended use, read the **official** model card first. + +--- + +## Quick start + +**1. Install** a recent [llama.cpp](https://github.com/ggml-org/llama.cpp) build (or use a GUI that bundles it). + +**2. Download** this repository: + +```bash +huggingface-cli download ryancook/chromadb-context-1-gguf --local-dir ./chromadb-context-1-gguf +``` + +**3. Run** (example — adjust paths and context length to your hardware): + +```bash +llama-cli -m ./chromadb-context-1-gguf/chromadb-context-1-Q4_0.gguf -cnv --color -ngl 99 +``` + +Swap the filename for any published `chromadb-context-1-*.gguf` from the **Files** tab (for example `Q4_K_M` or `MXFP4_MOE` when available). + +--- + +## Choosing a file + +**Start here (good defaults for most people):** + +| Priority | File pattern | When to use | +|----------|----------------|-------------| +| 1 | **`…-Q4_K_M.gguf`** or **`…-Q5_K_M.gguf`** | Best general-purpose balance of quality and size (if present in this repo). | +| 2 | **`…-MXFP4_MOE.gguf`** | Smaller MoE-oriented layout; strong choice when supported by your llama.cpp build/GPU stack. | +| 3 | **`…-Q4_0.gguf`** / **`…-Q5_0.gguf`** | Simpler legacy-style quants; predictable tradeoffs. | +| 4 | **`…-bf16.gguf`** | Full **BF16** fidelity (~40 GiB class); for reference or maximum quality when you have RAM/VRAM. | + +**Other presets** (IQ*, TQ*, Q2_K, Q3_K*, Q6_K, Q8_0, F16, …) may appear in the **Files** tab as they are published. Lower-bit and ternary formats are **experimental** for quality; profile on your workload before relying on them. + +> **Tip:** The **Files and versions** view on Hugging Face is authoritative for what is available in each commit. Filenames follow `chromadb-context-1-.gguf`. + +--- + +## Conversion pipeline + +Reproducible high-level steps: + +1. **Obtain** weights from [**chromadb/context-1**](https://huggingface.co/chromadb/context-1) (Apache 2.0). +2. **Convert** to GGUF with llama.cpp **`convert_hf_to_gguf.py`** (BF16 output from upstream bf16 checkpoint). +3. **Quantize** with **`llama-quantize`** using the preset named in each filename (`Q4_0`, `Q4_K_M`, `MXFP4_MOE`, etc.). + +### Reproducibility + +Conversions for this collection were produced with **[ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp)** at commit **`07ba6d275`** (short SHA; matches upstream `convert_hf_to_gguf.py` / `llama-quantize` from that tree). Newer llama.cpp revisions are generally backward compatible for GGUF loading, but you may see small numerical differences if you re-quantize. + +--- + +## Hardware & context + +- **VRAM / RAM:** MoE models route only a subset of experts per token; still treat published sizes as a guide and monitor peak usage at your target context length. +- **Context length:** Upstream supports a very long context window; practical limits depend on **KV cache size** and quant. Start with a smaller **`-c`** / context setting and increase only after you confirm stability. + +--- + +## License + +Same as upstream: **Apache 2.0**. Keep **[chromadb/context-1](https://huggingface.co/chromadb/context-1)** attribution visible when you redistribute or ship products built on these files. + +--- + +## More from Chroma + +- **Official model (safetensors):** [chromadb/context-1](https://huggingface.co/chromadb/context-1) +- **Chroma:** [trychroma.com](https://www.trychroma.com/) + + + + +<｜tool▁calls▁begin｜><｜tool▁call▁begin｜> +Shell \ No newline at end of file diff --git a/UPSTREAM.md b/UPSTREAM.md new file mode 100644 index 0000000..4c932b2 --- /dev/null +++ b/UPSTREAM.md @@ -0,0 +1,3 @@ +**Canonical source:** [chromadb/context-1](https://huggingface.co/chromadb/context-1) on Hugging Face (Apache 2.0). + +This directory is a derived GGUF distribution. Report model-quality or safety questions against the **official** upstream release, not this conversion, unless the issue reproduces only in GGUF form. diff --git a/chromadb-context-1-BF16.gguf b/chromadb-context-1-BF16.gguf new file mode 100644 index 0000000..7841611 --- /dev/null +++ b/chromadb-context-1-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1b5cbeb6cfe608542886957ef6b661001450da946eb1782c6dd497890ecabe +size 41860886816 diff --git a/chromadb-context-1-IQ2_M.gguf b/chromadb-context-1-IQ2_M.gguf new file mode 100644 index 0000000..c3bc81b --- /dev/null +++ b/chromadb-context-1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91cd51746e41264b75be709b5fb06ca9dbb37021337c9643c021d9ecea3ca622 +size 12065512736 diff --git a/chromadb-context-1-IQ2_S.gguf b/chromadb-context-1-IQ2_S.gguf new file mode 100644 index 0000000..a7a494a --- /dev/null +++ b/chromadb-context-1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f94a155f6108ab7922bdeb415266f74a70964079a9824c511368c7b28b63e8 +size 12065512736 diff --git a/chromadb-context-1-IQ3_M.gguf b/chromadb-context-1-IQ3_M.gguf new file mode 100644 index 0000000..7275ca2 --- /dev/null +++ b/chromadb-context-1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61f9fadb9248e7848e8d797127f13eb25560f067ee6a5e5d0c71cd8cca2f3fa +size 12202646816 diff --git a/chromadb-context-1-IQ3_S.gguf b/chromadb-context-1-IQ3_S.gguf new file mode 100644 index 0000000..e9e2bbc --- /dev/null +++ b/chromadb-context-1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89446baef009e3403d52c790d14abeb2afba1d3a8f4ae290394c5b916f742e12 +size 12065512736 diff --git a/chromadb-context-1-IQ3_XS.gguf b/chromadb-context-1-IQ3_XS.gguf new file mode 100644 index 0000000..db1411b --- /dev/null +++ b/chromadb-context-1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb22e76f25667fa55d000ac92eb690385863fda258c729c713438ea4195aa1d6 +size 12065512736 diff --git a/chromadb-context-1-IQ3_XXS.gguf b/chromadb-context-1-IQ3_XXS.gguf new file mode 100644 index 0000000..720976e --- /dev/null +++ b/chromadb-context-1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3e6ab92ca9d0765e47fcf64334e73fb29eaaa3c6764cdf38f593a792706ad77 +size 12165045536 diff --git a/chromadb-context-1-IQ4_NL.gguf b/chromadb-context-1-IQ4_NL.gguf new file mode 100644 index 0000000..519ba76 --- /dev/null +++ b/chromadb-context-1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9210bf34b48af00191c78be4974f37a2918a1dd95606e57a16850095956acc17 +size 12254625056 diff --git a/chromadb-context-1-IQ4_XS.gguf b/chromadb-context-1-IQ4_XS.gguf new file mode 100644 index 0000000..cf0a660 --- /dev/null +++ b/chromadb-context-1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ddeeffcd58e9aa34e0dfeecefc68b990229342d8e57f5b1d5b2bf7dd809507c +size 12245777696 diff --git a/chromadb-context-1-MXFP4_MOE.gguf b/chromadb-context-1-MXFP4_MOE.gguf new file mode 100644 index 0000000..c4dfdbe --- /dev/null +++ b/chromadb-context-1-MXFP4_MOE.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9254b99312acb069e0a30220d2ab03a9c1565127b74a3591b9856072b6a063c +size 12109565216 diff --git a/chromadb-context-1-Q2_K.gguf b/chromadb-context-1-Q2_K.gguf new file mode 100644 index 0000000..7614df9 --- /dev/null +++ b/chromadb-context-1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29fa22c11bcfbe94031e219f58a0081290fedbd0b762d8216004a4c897bfc403 +size 12065512736 diff --git a/chromadb-context-1-Q3_K_L.gguf b/chromadb-context-1-Q3_K_L.gguf new file mode 100644 index 0000000..b5d143e --- /dev/null +++ b/chromadb-context-1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b9f2cacf67946794bb6b3faf5dd9511eb29843c261fce8c0a17f85e7b0bbde6 +size 13335108896 diff --git a/chromadb-context-1-Q3_K_M.gguf b/chromadb-context-1-Q3_K_M.gguf new file mode 100644 index 0000000..b583e65 --- /dev/null +++ b/chromadb-context-1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe792c77b2cfe2b8878165920be236fce4fb84dff8a6de09f8595cb311dd819 +size 12916149536 diff --git a/chromadb-context-1-Q3_K_S.gguf b/chromadb-context-1-Q3_K_S.gguf new file mode 100644 index 0000000..5269ce2 --- /dev/null +++ b/chromadb-context-1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315e79e8d59aafa42cf5012c51c190c53c1df13b212b292fe3e7c6b07a84d690 +size 12061089056 diff --git a/chromadb-context-1-Q4_0.gguf b/chromadb-context-1-Q4_0.gguf new file mode 100644 index 0000000..51546d6 --- /dev/null +++ b/chromadb-context-1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f15b93b92e9774d72421c9e7463292fb3faaf75430a855a584cb7fc6862615d +size 12098690336 diff --git a/chromadb-context-1-Q4_1.gguf b/chromadb-context-1-Q4_1.gguf new file mode 100644 index 0000000..c6444c2 --- /dev/null +++ b/chromadb-context-1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd651b543444b048f8eea1c880f34ca2934d204baa25f8bbf11872fdf82d84a9 +size 13369092896 diff --git a/chromadb-context-1-Q4_K_M.gguf b/chromadb-context-1-Q4_K_M.gguf new file mode 100644 index 0000000..ecb334e --- /dev/null +++ b/chromadb-context-1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f8e99f2e30ddb64f1ab832a76a1845b8e13a6e0ad1a059d1391cb73bacb4177 +size 15805135136 diff --git a/chromadb-context-1-Q4_K_S.gguf b/chromadb-context-1-Q4_K_S.gguf new file mode 100644 index 0000000..b5ded97 --- /dev/null +++ b/chromadb-context-1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08f03f3fcd27f5b0fa840112e9784648fab1a2a1423956f153c9d269755ec690 +size 14654241056 diff --git a/chromadb-context-1-Q5_0.gguf b/chromadb-context-1-Q5_0.gguf new file mode 100644 index 0000000..53e6cc1 --- /dev/null +++ b/chromadb-context-1-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6a4138d04090f719547c4c5cb7e11e48803c16e438c08205713261ad517b8a +size 14639495456 diff --git a/chromadb-context-1-Q5_1.gguf b/chromadb-context-1-Q5_1.gguf new file mode 100644 index 0000000..d333046 --- /dev/null +++ b/chromadb-context-1-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a59ea704dc7169cc52439110fd45caaed309b7c38489fbcc9746ad3ffade233 +size 15909898016 diff --git a/chromadb-context-1-Q5_K_M.gguf b/chromadb-context-1-Q5_K_M.gguf new file mode 100644 index 0000000..ce6a47c --- /dev/null +++ b/chromadb-context-1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c2f100db5d0ba21be15f312e306b2a26aeafa18a88638cdd3d4b02fb439e19 +size 16893060896 diff --git a/chromadb-context-1-Q5_K_S.gguf b/chromadb-context-1-Q5_K_S.gguf new file mode 100644 index 0000000..51ca752 --- /dev/null +++ b/chromadb-context-1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ed6a3e9bbbea0885085fbf39ff44991c67ae53d82fe96898b8404566187443 +size 15892203296 diff --git a/chromadb-context-1-Q6_K.gguf b/chromadb-context-1-Q6_K.gguf new file mode 100644 index 0000000..2f66b9b --- /dev/null +++ b/chromadb-context-1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3c2390684042d239d37e8ff002ce31fa6ce8e26666fe4516f56e1c9831bc74 +size 22193343776 diff --git a/chromadb-context-1-Q8_0.gguf b/chromadb-context-1-Q8_0.gguf new file mode 100644 index 0000000..84d6286 --- /dev/null +++ b/chromadb-context-1-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f9fb360fca5c1919367e2217f8b15e9720936134483d3f0ec22e48cffdf998 +size 22261910816 diff --git a/chromadb-context-1-TQ1_0.gguf b/chromadb-context-1-TQ1_0.gguf new file mode 100644 index 0000000..142b34c --- /dev/null +++ b/chromadb-context-1-TQ1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60defe83ac3ad99f81bc2c96596126aec284e0c79b04e18391655d7b89dccb0c +size 12071549216 diff --git a/chromadb-context-1-TQ2_0.gguf b/chromadb-context-1-TQ2_0.gguf new file mode 100644 index 0000000..d356853 --- /dev/null +++ b/chromadb-context-1-TQ2_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b02501cb94836ac218ea07bd5be68fe318c062e86aa176e994e72e3117b635 +size 12084820256 diff --git a/chromadb-context-1-bf16.gguf b/chromadb-context-1-bf16.gguf new file mode 100644 index 0000000..527c8be --- /dev/null +++ b/chromadb-context-1-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c977ee963df556190fbaf7f720ae7822b8554611093b84e2779c5553b9ffb46 +size 41860886816