commit 8f18ef9c31ece563ddd89f3431f09a9dd66e5406 Author: ModelHub XC Date: Fri Sep 25 10:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-hf-ChatOrca-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a363679 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Llama-2-7b-hf-ChatOrca.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-hf-ChatOrca.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-hf-ChatOrca.IQ4_XS.gguf b/Llama-2-7b-hf-ChatOrca.IQ4_XS.gguf new file mode 100644 index 0000000..102db1a --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6fb9410ae0d3aedb704a830e4c8c7491e640600a77bfae547b2dddb82b142b +size 3647517984 diff --git a/Llama-2-7b-hf-ChatOrca.Q2_K.gguf b/Llama-2-7b-hf-ChatOrca.Q2_K.gguf new file mode 100644 index 0000000..de02d16 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f911e87bbf049cd0482b02532891eadd2b2316b0bebcfe9cd7a70454628303ee +size 2532865312 diff --git a/Llama-2-7b-hf-ChatOrca.Q3_K_L.gguf b/Llama-2-7b-hf-ChatOrca.Q3_K_L.gguf new file mode 100644 index 0000000..692b5bb --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ef03639fbbbcda58cc336357b6186b69674dd100a6baf8a6fa7f8da36d361e +size 3597112608 diff --git a/Llama-2-7b-hf-ChatOrca.Q3_K_M.gguf b/Llama-2-7b-hf-ChatOrca.Q3_K_M.gguf new file mode 100644 index 0000000..b98e372 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cbd0438cdf937e374e2978454295306229e4b9f45c50243b6dae7b81ed4019 +size 3298006304 diff --git a/Llama-2-7b-hf-ChatOrca.Q3_K_S.gguf b/Llama-2-7b-hf-ChatOrca.Q3_K_S.gguf new file mode 100644 index 0000000..dab3cbe --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89815cfb85e1047420f6f3349378b2964b3e2136b3692a33ade09bc200be8702 +size 2948306208 diff --git a/Llama-2-7b-hf-ChatOrca.Q4_K_M.gguf b/Llama-2-7b-hf-ChatOrca.Q4_K_M.gguf new file mode 100644 index 0000000..201a114 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e26f700d1d8d256f88ad3f836c6a118a83dc3072353131c5154301103feb3ae0 +size 4081005856 diff --git a/Llama-2-7b-hf-ChatOrca.Q4_K_S.gguf b/Llama-2-7b-hf-ChatOrca.Q4_K_S.gguf new file mode 100644 index 0000000..abda53b --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d090a01b47cc81778a01a1bf6b60bb7d14d90d1176902e6681d3ef6aae5c44 +size 3856741664 diff --git a/Llama-2-7b-hf-ChatOrca.Q5_K_M.gguf b/Llama-2-7b-hf-ChatOrca.Q5_K_M.gguf new file mode 100644 index 0000000..dc2ad3e --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104e5f218dd12f53a29b382871d46e6ad337c0589bb24f0833528232409925d0 +size 4783158560 diff --git a/Llama-2-7b-hf-ChatOrca.Q5_K_S.gguf b/Llama-2-7b-hf-ChatOrca.Q5_K_S.gguf new file mode 100644 index 0000000..0fd4ea4 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa00ce7d9a53a6aa8281616be4d39c65831f74e9afbf95563430fff242a4ffae +size 4651693344 diff --git a/Llama-2-7b-hf-ChatOrca.Q6_K.gguf b/Llama-2-7b-hf-ChatOrca.Q6_K.gguf new file mode 100644 index 0000000..56ca381 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42dc152b72f633151838aacdb5ddfefd4397bfc22517b40f35f18a4e535e48a6 +size 5529195808 diff --git a/Llama-2-7b-hf-ChatOrca.Q8_0.gguf b/Llama-2-7b-hf-ChatOrca.Q8_0.gguf new file mode 100644 index 0000000..2616ab1 --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2782a71a83df48f5851cabf8ca83d6550c360d9368256b6c5f26f8bcd44780b9 +size 7161091360 diff --git a/Llama-2-7b-hf-ChatOrca.f16.gguf b/Llama-2-7b-hf-ChatOrca.f16.gguf new file mode 100644 index 0000000..da63e3c --- /dev/null +++ b/Llama-2-7b-hf-ChatOrca.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec23432839686619834b01797ff7c0d80064f02b98fbae0992cc842f130ca44f +size 13478106400 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2af9df2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: manojpreveen/Llama-2-7b-hf-ChatOrca +datasets: +- iamplus/LLama2-SFT-Data +- iamplus/Open_Platypus_Orca +- iamplus/Orca +- iamplus/Conversational_Data +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/manojpreveen/Llama-2-7b-hf-ChatOrca + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-hf-ChatOrca-GGUF/resolve/main/Llama-2-7b-hf-ChatOrca.f16.gguf) | f16 | 13.6 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +