初始化项目，由ModelHub XC社区提供模型

Model: second-state/Bielik-4.5B-v3.0-Instruct-GGUF Source: Original Platform
2026-08-28 15:52:17 +08:00
commit 24ddb033dc
16 changed files with 203 additions and 0 deletions
--- a/.gitattributes
+++ 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-4.5B-v3.0-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Bielik-4.5B-v3.0-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Bielik-4.5B-v3.0-Instruct-Q2_K.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b47acb77c2c374273af504d3b4299687c1502531dcc261f83ebad582349872
+size 1771615232
--- a/Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2368a824cbc195b99ac15d1e83dd2443b5f1042faca605cacf0c676f39fdff39
+size 2499331072
--- a/Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee11e2e18ffde575cd8b7ffde0d75b691036ed5800f47286bfa110839d19476
+size 2303443968
--- a/Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a253faec870c89af2a3103cbb4fdbc48445eca2556bfc3dfec3252a0b8080159
+size 2077606912
--- a/Bielik-4.5B-v3.0-Instruct-Q4_0.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7b059817d84a0bc2457f9cf55ee2d6c4651ffeed756609f51af8252acb610d
+size 2700465152
--- a/Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fb78db7c5e1582d3ef5bded109cd98606aabd5acbb5c98601155174b6763e1
+size 2878886912
--- a/Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4672672c46c5425f7a98806f8aad058901db22b4f955ee2c4ee05ba31230ff
+size 2720453632
--- a/Bielik-4.5B-v3.0-Instruct-Q5_0.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed5506e8bbaf2f0715be34622ff2f76f055d9da1fba55437c8016b6b4173503
+size 3286684672
--- a/Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7635b12834ff15be6460e2d02fa197324c3a28f9a6b02bf53967a55c555fa305
+size 3378598912
--- a/Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2483fd4b365ef1b99bce1a5fa8d958027bf563d8ed63e7b33f6ed02d64d06761
+size 3286684672
--- a/Bielik-4.5B-v3.0-Instruct-Q6_K.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfc04bdfc0307a6d83c86f519d98de3d8957d84470ccdcb027ef7c5d5731300
+size 3909542912
--- a/Bielik-4.5B-v3.0-Instruct-Q8_0.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba97a6707abe252898d0788be8480e260d9aa4ca878145654fe02d17294be8f
+size 5061215232
--- a/Bielik-4.5B-v3.0-Instruct-f16.gguf
+++ b/Bielik-4.5B-v3.0-Instruct-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6006a5377a022b36926af59fdd303951def62e9baac4c14693511acb0f83acc
+size 9519301632
--- a/README.md
+++ b/README.md
@@ -0,0 +1,86 @@
+---
+base_model: speakleash/Bielik-4.5B-v3.0-Instruct
+license: apache-2.0
+model_creator: speakleash
+model_name: Bielik-4.5B-v3.0-Instruct
+quantized_by: Second State Inc.
+language:
+- pl
+library_name: transformers
+inference:
+  parameters:
+    temperature: 0.4
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Bielik-4.5B-v3.0-Instruct-GGUF
+
+## Original Model
+
+[speakleash/Bielik-4.5B-v3.0-Instruct](https://huggingface.co/speakleash/Bielik-4.5B-v3.0-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-4.5B-v3.0-Instruct-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --model-name Bielik-4.5B-v3.0-Instruct \
+    --prompt-template chatml \
+    --ctx-size 32000
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Bielik-4.5B-v3.0-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-4.5B-v3.0-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q2_K.gguf)     | Q2_K   | 2 | 1.77 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.50 GB| small, substantial quality loss |
+| [Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 2.30 GB| very small, high quality loss |
+| [Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 2.08 GB| very small, high quality loss |
+| [Bielik-4.5B-v3.0-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_0.gguf)     | Q4_0   | 4 | 2.70 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.88 GB| medium, balanced quality - recommended |
+| [Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.72 GB| small, greater quality loss |
+| [Bielik-4.5B-v3.0-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_0.gguf)     | Q5_0   | 5 | 3.29 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 3.38 GB| large, very low quality loss - recommended |
+| [Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 3.29 GB| large, low quality loss - recommended |
+| [Bielik-4.5B-v3.0-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q6_K.gguf)     | Q6_K   | 6 | 3.91 GB| very large, extremely low quality loss |
+| [Bielik-4.5B-v3.0-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q8_0.gguf)     | Q8_0   | 8 | 5.06 GB| very large, extremely low quality loss - not recommended |
+| [Bielik-4.5B-v3.0-Instruct-f16.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-f16.gguf)       | f16    | 16 | 9.52 GB| |
+
+*Quantized with llama.cpp b5201*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 4,
+  "pad_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 8192,
+  "mlp_bias": true,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}