From adcb2270114a7e7591d2bbacc66ed89309795471 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 27 May 2026 01:08:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: second-state/Starling-LM-7B-alpha-GGUF Source: Original Platform --- .gitattributes | 36 ++++++++++++++ README.md | 80 ++++++++++++++++++++++++++++++++ Starling-LM-7B-alpha-Q2_K.gguf | 3 ++ Starling-LM-7B-alpha-Q3_K_L.gguf | 3 ++ Starling-LM-7B-alpha-Q3_K_M.gguf | 3 ++ Starling-LM-7B-alpha-Q3_K_S.gguf | 3 ++ Starling-LM-7B-alpha-Q4_0.gguf | 3 ++ Starling-LM-7B-alpha-Q4_K_M.gguf | 3 ++ Starling-LM-7B-alpha-Q4_K_S.gguf | 3 ++ Starling-LM-7B-alpha-Q5_0.gguf | 3 ++ Starling-LM-7B-alpha-Q5_K_M.gguf | 3 ++ Starling-LM-7B-alpha-Q5_K_S.gguf | 3 ++ Starling-LM-7B-alpha-Q6_K.gguf | 3 ++ Starling-LM-7B-alpha-Q8_0.gguf | 3 ++ config.json | 25 ++++++++++ configuration.json | 1 + starling-lm-7b-alpha.Q5_K_M.gguf | 3 ++ 17 files changed, 181 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 Starling-LM-7B-alpha-Q2_K.gguf create mode 100644 Starling-LM-7B-alpha-Q3_K_L.gguf create mode 100644 Starling-LM-7B-alpha-Q3_K_M.gguf create mode 100644 Starling-LM-7B-alpha-Q3_K_S.gguf create mode 100644 Starling-LM-7B-alpha-Q4_0.gguf create mode 100644 Starling-LM-7B-alpha-Q4_K_M.gguf create mode 100644 Starling-LM-7B-alpha-Q4_K_S.gguf create mode 100644 Starling-LM-7B-alpha-Q5_0.gguf create mode 100644 Starling-LM-7B-alpha-Q5_K_M.gguf create mode 100644 Starling-LM-7B-alpha-Q5_K_S.gguf create mode 100644 Starling-LM-7B-alpha-Q6_K.gguf create mode 100644 Starling-LM-7B-alpha-Q8_0.gguf create mode 100644 config.json create mode 100644 configuration.json create mode 100644 starling-lm-7b-alpha.Q5_K_M.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7bc4049 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: berkeley-nest/Starling-LM-7B-alpha +datasets: +- berkeley-nest/Nectar +inference: false +library_name: transformers +license: cc-by-nc-4.0 +model_creator: Berkeley-Nest +model_name: Starling LM 7B Alpha +model_type: mistral +pipeline_tag: text-generation +quantized_by: Second State Inc. +language: +- en +tags: +- reward model +- RLHF +- RLAIF +--- + + + +
+ +
+
+ + +# Starling-LM-7B-alpha-GGUF + +## Original Model + +[berkeley-nest/Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `openchat` + + - Prompt string + + ```text + GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant: + ``` + + - Reverse prompt: `<|end_of_turn|>` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:starling-lm-7b-alpha.Q5_K_M.gguf llama-api-server.wasm -p openchat -r '<|end_of_turn|>' + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:starling-lm-7b-alpha.Q5_K_M.gguf llama-chat.wasm -p openchat -r '<|end_of_turn|>' + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Starling-LM-7B-alpha-Q2_K.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q2_K.gguf) | Q2_K | 2 | 2.7 GB| smallest, significant quality loss - not recommended for most purposes | +| [Starling-LM-7B-alpha-Q3_K_L.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [Starling-LM-7B-alpha-Q3_K_M.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [Starling-LM-7B-alpha-Q3_K_S.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [Starling-LM-7B-alpha-Q4_0.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Starling-LM-7B-alpha-Q4_K_M.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [Starling-LM-7B-alpha-Q4_K_S.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [Starling-LM-7B-alpha-Q5_0.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Starling-LM-7B-alpha-Q5_K_M.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [Starling-LM-7B-alpha-Q5_K_S.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended | +| [Starling-LM-7B-alpha-Q6_K.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [Starling-LM-7B-alpha-Q8_0.gguf](https://huggingface.co/second-state/Starling-LM-7B-alpha-GGUF/blob/main/Starling-LM-7B-alpha-Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| very large, extremely low quality loss - not recommended | diff --git a/Starling-LM-7B-alpha-Q2_K.gguf b/Starling-LM-7B-alpha-Q2_K.gguf new file mode 100644 index 0000000..e4b5301 --- /dev/null +++ b/Starling-LM-7B-alpha-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:292d93f14b08193eb982b624437db08946b1822618803e99abbd3531d76d2e74 +size 2701425824 diff --git a/Starling-LM-7B-alpha-Q3_K_L.gguf b/Starling-LM-7B-alpha-Q3_K_L.gguf new file mode 100644 index 0000000..dd1a674 --- /dev/null +++ b/Starling-LM-7B-alpha-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f26f4a6287ac621f645ef55e82e6abf20de719e8375e2bc63655cef59fa5181a +size 3822034912 diff --git a/Starling-LM-7B-alpha-Q3_K_M.gguf b/Starling-LM-7B-alpha-Q3_K_M.gguf new file mode 100644 index 0000000..4f16a0d --- /dev/null +++ b/Starling-LM-7B-alpha-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88aa629b98f30e16f86c0e85e6fff4c07dba5d664a5b46b03ce88cdf55146f61 +size 3518996448 diff --git a/Starling-LM-7B-alpha-Q3_K_S.gguf b/Starling-LM-7B-alpha-Q3_K_S.gguf new file mode 100644 index 0000000..2fbb1c0 --- /dev/null +++ b/Starling-LM-7B-alpha-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49561b6e4537601eb2b32d5f4425d2da18acb6905b8acff6173d5e2a39b99c4 +size 3164577760 diff --git a/Starling-LM-7B-alpha-Q4_0.gguf b/Starling-LM-7B-alpha-Q4_0.gguf new file mode 100644 index 0000000..20e3fbb --- /dev/null +++ b/Starling-LM-7B-alpha-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601df6a27f410903d52880c528049e65d9a5addd5c2a211578444c69f35be4e0 +size 4108928032 diff --git a/Starling-LM-7B-alpha-Q4_K_M.gguf b/Starling-LM-7B-alpha-Q4_K_M.gguf new file mode 100644 index 0000000..1ee9f34 --- /dev/null +++ b/Starling-LM-7B-alpha-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a735bf5f1b428b2cec4e78c7c83c0351a50f6e49542c627c6ffcc5b7ef3dc9ac +size 4368450592 diff --git a/Starling-LM-7B-alpha-Q4_K_S.gguf b/Starling-LM-7B-alpha-Q4_K_S.gguf new file mode 100644 index 0000000..018abd5 --- /dev/null +++ b/Starling-LM-7B-alpha-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e142599ba5a592f5cbecf4fc21bd24c22ce119787e4cb6739ae8d16e142ae2a1 +size 4140385312 diff --git a/Starling-LM-7B-alpha-Q5_0.gguf b/Starling-LM-7B-alpha-Q5_0.gguf new file mode 100644 index 0000000..a59725d --- /dev/null +++ b/Starling-LM-7B-alpha-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528fd64430fd90111def6a737f1f7979f21a93907f3b310dda924f9d72627243 +size 4997728288 diff --git a/Starling-LM-7B-alpha-Q5_K_M.gguf b/Starling-LM-7B-alpha-Q5_K_M.gguf new file mode 100644 index 0000000..e78fa88 --- /dev/null +++ b/Starling-LM-7B-alpha-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8022640fea02e50b294a5ca3b9701f753e3870f61c596b16e16e8fac4f130cea +size 5131421728 diff --git a/Starling-LM-7B-alpha-Q5_K_S.gguf b/Starling-LM-7B-alpha-Q5_K_S.gguf new file mode 100644 index 0000000..6c787f0 --- /dev/null +++ b/Starling-LM-7B-alpha-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25eb926b00b2ce4b0e877ba2590896cda901d2909add0826a460a23ae4165f1a +size 4997728288 diff --git a/Starling-LM-7B-alpha-Q6_K.gguf b/Starling-LM-7B-alpha-Q6_K.gguf new file mode 100644 index 0000000..29039eb --- /dev/null +++ b/Starling-LM-7B-alpha-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f1105040f0337bae1e38607caf5597c2071521bd4a860ff41cb930a0219869 +size 5942078560 diff --git a/Starling-LM-7B-alpha-Q8_0.gguf b/Starling-LM-7B-alpha-Q8_0.gguf new file mode 100644 index 0000000..267fb3c --- /dev/null +++ b/Starling-LM-7B-alpha-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64307c75fadac318fd8056371eca91cb391577e6589d96954b1576046ee3021 +size 7695875040 diff --git a/config.json b/config.json new file mode 100644 index 0000000..d758919 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "openchat/openchat_3.5", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 32000, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.0", + "use_cache": true, + "vocab_size": 32002 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/starling-lm-7b-alpha.Q5_K_M.gguf b/starling-lm-7b-alpha.Q5_K_M.gguf new file mode 100644 index 0000000..25911d7 --- /dev/null +++ b/starling-lm-7b-alpha.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6144d3a48352f5a40245ab1e89bfc0b17e4d045bf0e78fb512480f34ae92eba +size 5132357824