commit e7d3a7f2441f9b0a1e50d0d1bf45040d2a6e76ce Author: ModelHub XC Date: Thu Sep 17 00:00:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Bielik-11B-v2.3-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b018182 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Bielik-11B-v2.3-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Bielik-11B-v2.3-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Bielik-11B-v2.3-Instruct-Q2_K.gguf b/Bielik-11B-v2.3-Instruct-Q2_K.gguf new file mode 100644 index 0000000..c0c14d6 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfee6217db1af087b92e01c50a1561d1f9496c9a999caef44cbd076204a8c75 +size 4164338560 diff --git a/Bielik-11B-v2.3-Instruct-Q3_K_L.gguf b/Bielik-11B-v2.3-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..2f151d4 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5967b51b5e3022ce0575a4954fe6e60dfe373acfd904ac4d524b3b44a4b76a8 +size 5880001408 diff --git a/Bielik-11B-v2.3-Instruct-Q3_K_M.gguf b/Bielik-11B-v2.3-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..a3969ab --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efec8e622f4a8c27e24222416119364ac1029df2b36d1a1774c5890ed108ad0b +size 5404996480 diff --git a/Bielik-11B-v2.3-Instruct-Q3_K_S.gguf b/Bielik-11B-v2.3-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..6851c34 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7842c53cfcc984961b2a455f3cc7aa7bef79f0912cb780539553978521775b00 +size 4852724608 diff --git a/Bielik-11B-v2.3-Instruct-Q4_0.gguf b/Bielik-11B-v2.3-Instruct-Q4_0.gguf new file mode 100644 index 0000000..a45e9fe --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:324c939ac5e103d5aa567a08876f7138088cb99bf0d690ca2a5ae69044d27525 +size 6318547840 diff --git a/Bielik-11B-v2.3-Instruct-Q4_K_M.gguf b/Bielik-11B-v2.3-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..4dbb760 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a18bff3cb41a1619af6ac1d12024f141e872c4ade1d78cf02fb98334e6fc23 +size 6724051840 diff --git a/Bielik-11B-v2.3-Instruct-Q4_K_S.gguf b/Bielik-11B-v2.3-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..1b5d8c3 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae74e2dc2d2c0ba22f418b1a59fe84e62c10c46e9ae24dc163e17292135e7f7e +size 6364685184 diff --git a/Bielik-11B-v2.3-Instruct-Q5_0.gguf b/Bielik-11B-v2.3-Instruct-Q5_0.gguf new file mode 100644 index 0000000..c8023f7 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2585211b44cc175572fa14f6195709599638692cf0076da7fb376d194db18d7c +size 7698146176 diff --git a/Bielik-11B-v2.3-Instruct-Q5_K_M.gguf b/Bielik-11B-v2.3-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..c1553e9 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eba9199f9d9cc9eef11e5b9dd05e251322595e3d94afae087c29d114295e96b +size 7907042176 diff --git a/Bielik-11B-v2.3-Instruct-Q5_K_S.gguf b/Bielik-11B-v2.3-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..8b731e6 --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a5944beed79205cff9451376eef05bfefe16832d6686a4758b75b37e11b4997 +size 7698146176 diff --git a/Bielik-11B-v2.3-Instruct-Q6_K.gguf b/Bielik-11B-v2.3-Instruct-Q6_K.gguf new file mode 100644 index 0000000..f70211b --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8faf26442129eee46e1fd35b7b920ef69a14740100cecec0465855b2facaf3a +size 9163969408 diff --git a/Bielik-11B-v2.3-Instruct-Q8_0.gguf b/Bielik-11B-v2.3-Instruct-Q8_0.gguf new file mode 100644 index 0000000..8ca3fbf --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37be1b0a98474918f6a129b6140cae683a339324e02b3f32e76ec310be0d64d +size 11868812160 diff --git a/Bielik-11B-v2.3-Instruct-f16.gguf b/Bielik-11B-v2.3-Instruct-f16.gguf new file mode 100644 index 0000000..e743c5f --- /dev/null +++ b/Bielik-11B-v2.3-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93dcc9e605ee1e223a590deeeb561204b24e5e5055919770c302732063dfbceb +size 22339171200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..28545d1 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: speakleash/Bielik-11B-v2.3-Instruct +license: apache-2.0 +model_creator: speakleash +model_name: Bielik-11B-v2.3-Instruct +quantized_by: Second State Inc. +language: +- pl +library_name: transformers +inference: + parameters: + temperature: 0.2 +--- + + + +
+ +
+
+ + +# Bielik-11B-v2.3-Instruct-GGUF + +## Original Model + +[speakleash/Bielik-11B-v2.3-Instruct](https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.18.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.3) + +- Prompt template + + - Prompt type: `chatml` + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {prompt}<|im_end|> + <|im_start|>assistant + ``` + +- Context size: `32000` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bielik-11B-v2.3-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name Bielik-11B-v2.3-Instruct \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bielik-11B-v2.3-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 32000 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Bielik-11B-v2.3-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q2_K.gguf) | Q2_K | 2 | 4.16 GB| smallest, significant quality loss - not recommended for most purposes | +| [Bielik-11B-v2.3-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 5.88 GB| small, substantial quality loss | +| [Bielik-11B-v2.3-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 5.40 GB| very small, high quality loss | +| [Bielik-11B-v2.3-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 4.85 GB| very small, high quality loss | +| [Bielik-11B-v2.3-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q4_0.gguf) | Q4_0 | 4 | 6.32 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Bielik-11B-v2.3-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 6.72 GB| medium, balanced quality - recommended | +| [Bielik-11B-v2.3-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 6.36 GB| small, greater quality loss | +| [Bielik-11B-v2.3-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q5_0.gguf) | Q5_0 | 5 | 7.70 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Bielik-11B-v2.3-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 7.91 GB| large, very low quality loss - recommended | +| [Bielik-11B-v2.3-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 7.70 GB| large, low quality loss - recommended | +| [Bielik-11B-v2.3-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q6_K.gguf) | Q6_K | 6 | 9.16 GB| very large, extremely low quality loss | +| [Bielik-11B-v2.3-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-Q8_0.gguf) | Q8_0 | 8 | 11.9 GB| very large, extremely low quality loss - not recommended | +| [Bielik-11B-v2.3-Instruct-f16.gguf](https://huggingface.co/second-state/Bielik-11B-v2.3-Instruct-GGUF/blob/main/Bielik-11B-v2.3-Instruct-f16.gguf) | f16 | 16 | 22.3 GB| | + +*Quantized with llama.cpp b5201* \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..750c9a0 --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 32001, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 50, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.44.2", + "use_cache": true, + "vocab_size": 32128 +}