commit 50b7e58b066948275c3e1f0047b1f649f762adbd Author: ModelHub XC Date: Fri Jul 31 18:55:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TeichAI/Qwen3-8B-Gemini-2.5-Flash-Distill-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..63bf4f2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Gemini-2.5-Flash-Distill-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-8B-Gemini-2.5-Flash-Distill-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-8b.F16.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..04bad72 --- /dev/null +++ b/Modelfile @@ -0,0 +1,59 @@ + +FROM qwen3-8b.Q8_0.gguf +TEMPLATE """{{- 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 XML tags: + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within XML tags: + +{"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 }}""" +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|im_start|>" +PARAMETER temperature 0.6 +PARAMETER min_p 0.0 +PARAMETER top_k 20 +PARAMETER top_p 0.95 +PARAMETER repeat_penalty 1 \ No newline at end of file diff --git a/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_m.gguf b/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_m.gguf new file mode 100644 index 0000000..932d858 --- /dev/null +++ b/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c0b2ca5c43279fdfbb7256e0b6aa1595bcb93b728496f0deaf45d7615a7eee6 +size 4124161920 diff --git a/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_s.gguf b/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_s.gguf new file mode 100644 index 0000000..39ebfcc --- /dev/null +++ b/Qwen3-8B-Gemini-2.5-Flash-Distill-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3957d4cc4b5e8402e3b17768798b877cb4c151b53afdcf124e81f08038850c2d +size 3769612160 diff --git a/Qwen3-8B-Gemini-2.5-Flash-Distill-q4_k_m.gguf b/Qwen3-8B-Gemini-2.5-Flash-Distill-q4_k_m.gguf new file mode 100644 index 0000000..b9e7058 --- /dev/null +++ b/Qwen3-8B-Gemini-2.5-Flash-Distill-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08147887157b107ed98c00291ad5b0515217082aa255bc8c2930a7dc786d86dd +size 5027784576 diff --git a/Qwen3-8B-Gemini-2.5-Flash-Distill-q8_0.gguf b/Qwen3-8B-Gemini-2.5-Flash-Distill-q8_0.gguf new file mode 100644 index 0000000..36e3b0f --- /dev/null +++ b/Qwen3-8B-Gemini-2.5-Flash-Distill-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7425bb564f3538c673435c57a4a0f6ad5ff37fcfdeaf6a30c27d73a2d1e0ac +size 8709519232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b67849e --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +base_model: +- TeichAI/Qwen3-8B-Gemini-2.5-Flash-Distill +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +license: apache-2.0 +language: +- en +datasets: +- TeichAI/gemini-2.5-flash-11000x +--- + +# Qwen3 8B x Gemini 2.5 Flash Distill + +This model was trained on a large **Gemini 2.5 Flash** dataset. + +- 🤖 Related Models: +| Model | Effective parameters | Active parameters | +| ------------- | ------------- | ------------- | +| [`TeichAI/Qwen3-30B-A3B-Thinking-2507-Gemini-2.5-Flash-Distill-GGUF`](https://huggingface.co/TeichAI/Qwen3-30B-A3B-Thinking-2507-Gemini-2.5-Flash-Distill-GGUF) | 30 B | 3 B | +| [`TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill-GGUF`](https://huggingface.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill-GGUF) | 4 B | 4 B | + + +- 🧬 Datasets: + - `TeichAI/gemini-2.5-flash-11000x` + +- 🏗 Base Model: + - `unsloth/Qwen3-8B` + +- ⚡ Use cases: + - Coding + - Science + - Legal + - History + - Marketing + - General Purpose + +- ∑ Stats (Dataset) + - Costs: $ 134 (USD) + - Total tokens (input + output): 54.4 M \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6b5bfe8 --- /dev/null +++ b/config.json @@ -0,0 +1,70 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "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", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151654, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.56.2", + "unsloth_fixed": true, + "unsloth_version": "2025.11.3", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/qwen3-8b.F16.gguf b/qwen3-8b.F16.gguf new file mode 100644 index 0000000..d989963 --- /dev/null +++ b/qwen3-8b.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f447ac97203f75a4fbb8f1fd24119eaee8bcf106eb5989c2a803afa99551b8 +size 16388043552