初始化项目，由ModelHub XC社区提供模型

Model: ALFHAzero/YuiAirillama
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+llama-3.2-3b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.2-3b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3.2-3b-instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-1.9-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Yui16bit-1.9-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+modelgemma2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-2-2b.F16.gguf filter=lfs diff=lfs merge=lfs -text
+model-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,57 @@
+
+FROM llama-3.2-3b-instruct.F16.gguf
+TEMPLATE """{{ if .Messages }}
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+{{- if .System }}
+
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question.
+{{- end }}
+{{- end }}<|eot_id|>
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+{{- if and $.Tools $last }}
+
+Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+
+{{ $.Tools }}
+{{- end }}
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+{{- if .ToolCalls }}
+
+{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+{{- else }}
+
+{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
+{{- end }}
+{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"""
+PARAMETER stop "<|start_header_id|>"
+PARAMETER stop "<|end_header_id|>"
+PARAMETER stop "<|eot_id|>"
+PARAMETER stop "<|eom_id|>"
+PARAMETER temperature 1.5
+PARAMETER min_p 0.1

README.md

@@ -0,0 +1,21 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+
+---
+
+# YuiAirillama - GGUF
+
+This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
+
+**Example usage**:
+- For text only LLMs:    **llama-cli** **--hf** repo_id/model_name **-p** "why is the sky blue?"
+- For multimodal models: **llama-mtmd-cli** **-m** model_name.gguf **--mmproj** mmproj_file.gguf
+
+## Available Model files:
+- `llama-3.2-3b-instruct.F16.gguf`
+
+## Ollama
+An Ollama Modelfile is included for easy deployment.

Yui16bit-1.9-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c507ca380ca4992b2985517d3ca04d0bd0eaf82643d823e989afcf0077965c55
+size 6433688832

Yui16bit-1.9-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d85e54ab76b7f48e827e11e9190bda3778b4dd952a836d30b250ef4386ce3c
+size 3421900032

Yui16bit-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed127b9fddc607aeec0b2d48ec70be53e1ccefa21beb1b8e44df7ebfc264e306
+size 3421900032

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "torch_dtype": "float16",
+    "eos_token_id": 128009,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": 128004,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 32.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": true,
+    "transformers_version": "4.56.2",
+    "unsloth_fixed": true,
+    "unsloth_version": "2025.10.9",
+    "use_cache": true,
+    "vocab_size": 128256
+}

gemma-2-2b.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c213e333370b48b8651d09c5c3769fe51f1fcf202652938d394d06387a113b
+size 5235214848

gemma-2-2b.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1975e1b9362f724a3e8ce3e4c7b02af72448d4b25196de2ce8c507967c853903
+size 1708583424

llama-3.2-3b-instruct.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833ded739792f00fe6e4205969b1b131794203a0f897eb7964035cc4aa9418c0
+size 6433688512

llama-3.2-3b-instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390e74370f1b3ef64626cfc33376a2355e0db7b984592a6efa247b75bff92be1
+size 2019378112

llama-3.2-3b-instruct.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2890cf7d4df173f1e59ba0fbb1f2674f9322143a7607edb8d9037cbf0917e3
+size 3421899712

model-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44ea7cfd9223b16137b5c5bea570a67e050949bf88a824866914d7cad747448
+size 291545184

modelgemma2-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a09dcab0b244757c0b1d933feabf36020343e669f7d22aed78e0f21bb350a75
+size 2784495968