初始化项目，由ModelHub XC社区提供模型

Model: eryk-mazus/polka-1.1b-chat-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,40 @@
+*.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
+polka-1.1b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+polka-1.1b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+polka-1.1b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+polka-1.1b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+polka-1.1b-chat-F16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+base_model: eryk-mazus/polka-1.1b-chat
+inference: false
+language:
+- pl
+license: apache-2.0
+model_name: Polka-1.1B-Chat
+model_type: tinyllama
+model_creator: Eryk Mazuś
+prompt_template: '<|im_start|>system
+
+  {system_message}<|im_end|>
+
+  <|im_start|>user
+
+  {prompt}<|im_end|>
+
+  <|im_start|>assistant
+
+  '
+---
+
+*I've copy-pased some information from TheBloke's model cards, hope it's ok*
+
+For a model of this size, with stronger quantization, quality appears to decline much more than for larger models. Personally, I would advise to stick with `fp16` or `int8` for this model.
+
+## Prompt template: ChatML
+
+```
+<|im_start|>system
+Jesteś pomocnym asystentem.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+## Example `llama.cpp` command
+
+```shell
+./main -m ./polka-1.1b-chat-gguf/polka-1.1b-chat-Q8_0.gguf --color -c 2048 --temp 0.2 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\nJesteś pomocnym asystentem.<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
+```
+
+Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
+
+Change `-c 2048` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
+
+If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "eryk-mazus/polka-1.1b-sft",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 43882,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 43904
+}

polka-1.1b-chat-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c569f0bd1d01f1dc329bc0e29439c37ec75d291d4c02a8d27b4c12cd5b768f
+size 2192720000

polka-1.1b-chat-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f2c486da0613fa5fd2942b64ebe0a43665fab4ea04d7a60691604d5f46f31a
+size 701784192

polka-1.1b-chat-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6208edbc44c5ec731e8d4385d22614508299d8893613d9fe77e6045e9289adaa
+size 819060864

polka-1.1b-chat-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4da487cfba2cb8ada970dcbcf3c4fca888cdbb63ecbb1e9ee5c88834d52474
+size 803045504

polka-1.1b-chat-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79041229836cbf451bb91aec75de0191a405e1d269cfd956d3d72cc9d921ff7b
+size 1221871744