初始化项目，由ModelHub XC社区提供模型

Model: ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1-GGUF Source: Original Platform
2026-07-24 10:02:07 +08:00
commit dd4d576f6a
26 changed files with 286 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,58 @@
+*.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
+Turkish-Llama-8b-Instruct-v0.1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Turkish-Llama-8b-Instruct-v0.1-F16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,110 @@
+---
+base_model: ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1
+license: llama3
+language:
+- tr
+- en
+tags:
+- gguf
+- ggml
+- llama3
+- cosmosllama
+- turkish llama
+---
+# CosmsoLLaMa GGUFs
+
+## Objective
+Due to the need for quantized models in real-time applications, we introduce our GGUF formatted models. These models are part of 
+GGML project with a hope to democratize the use of Large Models. Depending on the quantization type, there are 20+ models.
+
+### Features
+* All quantization details are listed on the right by Hugging Face.
+* All the models have been tested in `llama.cpp` environments, `llama-cli` and `llama-server`. 
+* Furthermore, a YouTube video has been made to introduce the basics of using `lmstudio` to utilize these models. 👇
+[![lmstudio_yt](https://img.youtube.com/vi/JRID-6sRl7I/0.jpg)](https://www.youtube.com/watch?v=JRID-6sRl7I)
+
+
+### Code Example
+Usage example with `llama-cpp-python`
+
+```py
+from llama_cpp import Llama
+
+# Define the inference parameters
+inference_params = {
+    "n_threads": 4,
+    "n_predict": -1,
+    "top_k": 40,
+    "min_p": 0.05,
+    "top_p": 0.95,
+    "temp": 0.8,
+    "repeat_penalty": 1.1,
+    "input_prefix": "<|start_header_id|>user<|end_header_id|>\\n\\n",
+    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n",
+    "antiprompt": [],
+    "pre_prompt": "Sen bir yapay zeka asistanısın. Kullanıcı sana bir görev verecek. Amacın görevi olabildiğince sadık bir şekilde tamamlamak.",
+    "pre_prompt_suffix": "<|eot_id|>",
+    "pre_prompt_prefix": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\n",
+    "seed": -1,
+    "tfs_z": 1,
+    "typical_p": 1,
+    "repeat_last_n": 64,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n_keep": 0,
+    "logit_bias": {},
+    "mirostat": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "memory_f16": True,
+    "multiline_input": False,
+    "penalize_nl": True
+}
+
+# Initialize the Llama model with the specified inference parameters
+llama = Llama.from_pretrained(
+    repo_id="ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1-GGUF",
+    filename="*Q4_K.gguf",
+    verbose=False
+)
+# Example input
+user_input = "Türkiyenin başkenti neresidir?"
+
+# Construct the prompt
+prompt = f"{inference_params['pre_prompt_prefix']}{inference_params['pre_prompt']}\n\n{inference_params['input_prefix']}{user_input}{inference_params['input_suffix']}"
+
+# Generate the response
+response = llama(prompt)
+
+# Output the response
+print(response['choices'][0]['text'])
+
+```
+
+The quantization has been made using `llama.cpp`. As we have seen, this method tends to give the most stable results.
+
+Obviously, we encountered better inference quality for models with the highest bits. However, the inference time tends to be similar between low-bit models. 
+
+Each model's memory footprint can be anticipated by the qunatization docs in either [Hugging Face](https://huggingface.co/docs/transformers/main/en/quantization/overview) or [llama.cpp](https://github.com/ggerganov/llama.cpp/tree/master/examples/quantize).
+
+
+# Acknowledgments
+- Research supported with Cloud TPUs from [Google's TensorFlow Research Cloud](https://sites.research.google/trc/about/) (TFRC). Thanks for providing access to the TFRC ❤️
+- Thanks to the generous support from the Hugging Face team, it is possible to download models from their S3 storage 🤗
+
+# Citation
+```bibtex
+@inproceedings{kesgin2024optimizing,
+  title={Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training},
+  author={Kesgin, H Toprak and Yuce, M Kaan and Dogan, Eren and Uzun, M Egemen and Uz, Atahan and {\.I}nce, Elif and Erdem, Yusuf and Shbib, Osama and Zeer, Ahmed and Amasyali, M Fatih},
+  booktitle={2024 Innovations in Intelligent Systems and Applications Conference (ASYU)},
+  pages={1--6},
+  year={2024},
+  organization={IEEE}
+}
+```
+
+## Contact
+COSMOS AI Research Group, Yildiz Technical University Computer Engineering Department  
+https://cosmos.yildiz.edu.tr/  
+cosmos@yildiz.edu.tr
--- a/Turkish-Llama-8b-Instruct-v0.1-F16.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6366fbcbd5a7a20b05bece7e59c79b8199f74669c5f946f909b579eabf737c
+size 16068890880
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ2_M.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ2_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e937e3bce0ba33e62a7a31f9d9ff05dc5eb53ad4f71c54311adf859cdf3f6bf
+size 619983104
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ3_M.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ3_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d52678b6096d2a82051347bc6cfdf7bc6cd2f63833014c7cb2bbb2d9579ec5c
+size 3784823040
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ3_S.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ3_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebaa32460d3d6fe10050d06462a30aac2e59cc1ee3eea5ac15acdb4e971999f
+size 3682324736
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ3_XS.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ3_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021b7ef6dfc0b78f293e3a18db02f42c673a762ff556a83f4335d5aa1d3b92dd
+size 3518746880
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ3_XXS.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ3_XXS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fa7886a2abaa87175d86a411b9d5b5b3bed7b8fdc43f3cfa386e8e8e1455c5
+size 672755968
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ4_NL.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ4_NL.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5659905a31c1cc01c940b4a03922296e5d5e0a736d072a9e1d761bbb77bd521b
+size 4707348736
--- a/Turkish-Llama-8b-Instruct-v0.1.IQ4_XS.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.IQ4_XS.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af928919f2c62a5747760806fc6558fe7eef6fe9f000edd7b0fb3eeb288f7d3
+size 4484362496
--- a/Turkish-Llama-8b-Instruct-v0.1.Q2_K.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:501419efc878342a820e866f79c6ee44c6c7ce12c26f07921d66b8e42433e2d5
+size 3179131136
--- a/Turkish-Llama-8b-Instruct-v0.1.Q3_K.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q3_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84948a77eafff58cecbb583f9cafb3f057522829148b69db238db9d382bbc27
+size 4018917632
--- a/Turkish-Llama-8b-Instruct-v0.1.Q3_K_L.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523ca4a46505afe45a742d4c34e4e0bc9740c20d30fbac2c5cda01cf3b88f0da
+size 4321956096
--- a/Turkish-Llama-8b-Instruct-v0.1.Q3_K_M.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84948a77eafff58cecbb583f9cafb3f057522829148b69db238db9d382bbc27
+size 4018917632
--- a/Turkish-Llama-8b-Instruct-v0.1.Q3_K_S.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565c7ef7795cdf3a3439660ebab202085c43854e8831e42bc4706e51ac6d1fd0
+size 3664498944
--- a/Turkish-Llama-8b-Instruct-v0.1.Q4_K.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q4_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e483f791cf679ea6536f696d7b585793807a4bac31522da8eaaa3e0dee8a5896
+size 4920733952
--- a/Turkish-Llama-8b-Instruct-v0.1.Q4_K_M.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e483f791cf679ea6536f696d7b585793807a4bac31522da8eaaa3e0dee8a5896
+size 4920733952
--- a/Turkish-Llama-8b-Instruct-v0.1.Q4_K_S.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94563c915b2468f8900cded3464021f9c38202643e2c7535cc2fa4fc9ffa79f7
+size 4692668672
--- a/Turkish-Llama-8b-Instruct-v0.1.Q5_0.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf7ab9a51510445de83f8bd23bd3ee44d8dc24e47ae8d4dac13a735e03e1042
+size 5599293696
--- a/Turkish-Llama-8b-Instruct-v0.1.Q5_1.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef51c7477b96c3d07b809cabff4d1594011f6bca10cb8ebdb99da376d6185186
+size 6068334848
--- a/Turkish-Llama-8b-Instruct-v0.1.Q5_K.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q5_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20a91b9ae6654d4d5acbdfab32480d1f203347e654b320efe19bca7936d94a2
+size 5732987136
--- a/Turkish-Llama-8b-Instruct-v0.1.Q5_K_M.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20a91b9ae6654d4d5acbdfab32480d1f203347e654b320efe19bca7936d94a2
+size 5732987136
--- a/Turkish-Llama-8b-Instruct-v0.1.Q5_K_S.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c42f76bfc17f1205c6d0409b1593e5b06e345b5336fd11d0f800cd6f926c96
+size 5599293696
--- a/Turkish-Llama-8b-Instruct-v0.1.Q6_K.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ce9442d5a7fe21eb9f79df7b30c70dbd4e5e7e29ee10ae447a40b5595c7ea9e
+size 6596006144
--- a/Turkish-Llama-8b-Instruct-v0.1.Q8_0.gguf
+++ b/Turkish-Llama-8b-Instruct-v0.1.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e15b58cb80e3ef24d5acba418441b0c2bf69853d37403d2c4c5ea2b63b34de5
+size 8540770560
--- a/cosmos_lm_studio.preset.json
+++ b/cosmos_lm_studio.preset.json
@@ -0,0 +1,49 @@
+{
+  "name": "cosmos_lm_studio",
+  "load_params": {
+    "n_ctx": 2048,
+    "n_batch": 512,
+    "rope_freq_base": 0,
+    "rope_freq_scale": 0,
+    "n_gpu_layers": 10,
+    "use_mlock": true,
+    "main_gpu": 0,
+    "tensor_split": [
+      0
+    ],
+    "seed": -1,
+    "f16_kv": true,
+    "use_mmap": true,
+    "no_kv_offload": false,
+    "num_experts_used": 0
+  },
+  "inference_params": {
+    "n_threads": 4,
+    "n_predict": -1,
+    "top_k": 40,
+    "min_p": 0.05,
+    "top_p": 0.95,
+    "temp": 0.8,
+    "repeat_penalty": 1.1,
+    "input_prefix": "<|start_header_id|>user<|end_header_id|>\\n\\n",
+    "input_suffix": "<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n",
+    "antiprompt": [],
+    "pre_prompt": "Sen bir yapay zeka asistanısın. Kullanıcı sana bir görev verecek. Amacın görevi olabildiğince sadık bir şekilde tamamlamak. Görevi yerine getirirken adım adım düşün ve adımlarını gerekçelendir.",
+    "pre_prompt_suffix": "<|eot_id|>",
+    "pre_prompt_prefix": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\n",
+    "seed": -1,
+    "tfs_z": 1,
+    "typical_p": 1,
+    "repeat_last_n": 64,
+    "frequency_penalty": 0,
+    "presence_penalty": 0,
+    "n_keep": 0,
+    "logit_bias": {},
+    "mirostat": 0,
+    "mirostat_tau": 5,
+    "mirostat_eta": 0.1,
+    "memory_f16": true,
+    "multiline_input": false,
+    "penalize_nl": true
+  }
+}