commit 92b285b8a3bf1619fd4ad38af43ea58b9e254f0e Author: ModelHub XC Date: Fri Oct 16 06:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: atsintli/model_sonbee_8bits Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..db569f7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,38 @@ +*.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 +unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-1.5b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen2.5-coder-1.5b-instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..75300cc --- /dev/null +++ b/Modelfile @@ -0,0 +1,54 @@ + +FROM qwen2.5-coder-1.5b-instruct.F16.gguf +TEMPLATE """{{- if .Suffix }}<|fim_prefix|>{{ .Prompt }}<|fim_suffix|>{{ .Suffix }}<|fim_middle|> +{{- else if .Messages }} +{{- if or .System .Tools }}<|im_start|>system +{{- if .System }} +{{ .System }} +{{- end }} +{{- if .Tools }} + +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within : + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within with NO other text. Do not include any backticks or ```json. + +{"name": , "arguments": } + +{{- end }}<|im_end|> +{{ end }} +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 -}} +{{- if eq .Role "user" }}<|im_start|>user +{{ .Content }}<|im_end|> +{{ else if eq .Role "assistant" }}<|im_start|>assistant +{{ if .Content }}{{ .Content }} +{{- else if .ToolCalls }} +{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} +{{ end }} +{{- end }}{{ if not $last }}<|im_end|> +{{ end }} +{{- else if eq .Role "tool" }}<|im_start|>user + +{{ .Content }} +<|im_end|> +{{ end }} +{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant +{{ end }} +{{- end }} +{{- else }} +{{- if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""" +SYSTEM """You are Qwen, created by Alibaba Cloud. You are a helpful assistant.""" \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..2864179 --- /dev/null +++ b/README.md @@ -0,0 +1,23 @@ +--- +tags: +- gguf +- llama.cpp +- unsloth + +--- + +# model_sonbee_8bits : 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 atsintli/model_sonbee_8bits --jinja` +- For multimodal models: `llama-mtmd-cli -hf atsintli/model_sonbee_8bits --jinja` + +## Available Model files: +- `qwen2.5-coder-1.5b-instruct.F16.gguf` + +## Ollama +An Ollama Modelfile is included for easy deployment. +This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) +[](https://github.com/unslothai/unsloth) diff --git a/config.json b/config.json new file mode 100644 index 0000000..b0bbd4d --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "float16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "unsloth_version": "2026.8.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/qwen2.5-coder-1.5b-instruct.F16.gguf b/qwen2.5-coder-1.5b-instruct.F16.gguf new file mode 100644 index 0000000..756d55f --- /dev/null +++ b/qwen2.5-coder-1.5b-instruct.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12f5d3ed463dc6cbc154c814af283c7cd36fc1f346e031b16419bf735d4addb +size 3093668960 diff --git a/qwen2.5-coder-1.5b-instruct.Q8_0.gguf b/qwen2.5-coder-1.5b-instruct.Q8_0.gguf new file mode 100644 index 0000000..ffd1a75 --- /dev/null +++ b/qwen2.5-coder-1.5b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94e27009fa68db9cf0259ee3a355da84eb1e8259137b123871b67a5391a5e6ce +size 1646572640 diff --git a/unsloth.Q8_0.gguf b/unsloth.Q8_0.gguf new file mode 100644 index 0000000..b3a28a6 --- /dev/null +++ b/unsloth.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ab37529aff49b836f05fa32ff3a19453bd1d3879fde8ce7d1c1456edb96ca3 +size 8098524960