From 0da4f955c79f473bb907d0c37fc2a0a734e8b519 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 11 Jun 2026 05:14:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Shinzmann/naija-petro-GGUF Source: Original Platform --- .gitattributes | 39 +++++++++++ Modelfile | 59 +++++++++++++++++ Qwen3-32B.BF16-00002-of-00002.gguf | 3 + Qwen3-32B.Q4_K_M.gguf | 3 + Qwen3-32B.Q5_K_M.gguf | 3 + Qwen3-32B.Q8_0.gguf | 3 + README.md | 48 ++++++++++++++ config.json | 100 +++++++++++++++++++++++++++++ 8 files changed, 258 insertions(+) create mode 100644 .gitattributes create mode 100644 Modelfile create mode 100644 Qwen3-32B.BF16-00002-of-00002.gguf create mode 100644 Qwen3-32B.Q4_K_M.gguf create mode 100644 Qwen3-32B.Q5_K_M.gguf create mode 100644 Qwen3-32B.Q8_0.gguf create mode 100644 README.md create mode 100644 config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3790bd0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +Qwen3-32B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B.BF16-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-32B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..7659623 --- /dev/null +++ b/Modelfile @@ -0,0 +1,59 @@ + +FROM Qwen3-32B.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/Qwen3-32B.BF16-00002-of-00002.gguf b/Qwen3-32B.BF16-00002-of-00002.gguf new file mode 100644 index 0000000..5c8f38c --- /dev/null +++ b/Qwen3-32B.BF16-00002-of-00002.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f74ef6d23b3cf787ba60d21c8912745e03e0630ddd0afb305d01044fe16804e3 +size 15659811424 diff --git a/Qwen3-32B.Q4_K_M.gguf b/Qwen3-32B.Q4_K_M.gguf new file mode 100644 index 0000000..92b2f05 --- /dev/null +++ b/Qwen3-32B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a49e4b593eda8bbc997c00b4b352722a05e593b1505c84c0475cac67d5f81523 +size 19762149568 diff --git a/Qwen3-32B.Q5_K_M.gguf b/Qwen3-32B.Q5_K_M.gguf new file mode 100644 index 0000000..018ee78 --- /dev/null +++ b/Qwen3-32B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef5a0f984cdbb5a5e0b2ca18b5beec5785033f21682146d427a467442ff4f55d +size 23214831808 diff --git a/Qwen3-32B.Q8_0.gguf b/Qwen3-32B.Q8_0.gguf new file mode 100644 index 0000000..42fa839 --- /dev/null +++ b/Qwen3-32B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c8c64b438ff2022e81a3eeadfa1f524d97c2e95ea6370ab3afa1a8331f538e +size 34817719488 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9761881 --- /dev/null +++ b/README.md @@ -0,0 +1,48 @@ +--- +license: apache-2.0 +language: +- en +base_model: Shinzmann/naija-petro +pipeline_tag: text-generation +tags: +- petroleum-engineering +- oil-and-gas +- nigeria +- qwen3 +- gguf +- llama-cpp +- ollama +- quantized +--- + +# Naija-Petro (32B) — GGUF + +GGUF quantizations of [`Shinzmann/naija-petro`](https://huggingface.co/Shinzmann/naija-petro) (the 32B variant) for inference with [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://ollama.com), LM Studio, and compatible runtimes. + +See the full [model card](https://huggingface.co/Shinzmann/naija-petro) for training details, intended use, and limitations. For a lighter footprint, consider the [8B GGUF](https://huggingface.co/Shinzmann/naija-petro-8b-GGUF). For Nigeria-specific accuracy, use these weights with the [Naija-Petro RAG system](https://github.com/Mystique1337/naija-petro). + +## Available quantizations + +| File suffix | Method | Notes | +|---|---|---| +| `Q4_K_M` | 4-bit (k-quant, medium) | Smallest; recommended default for 32B on limited RAM/VRAM | +| `Q5_K_M` | 5-bit (k-quant, medium) | Higher quality, larger | +| `Q8_0` | 8-bit | Near-lossless; largest and slowest | + +> 32B GGUF files are large. Q4_K_M is the practical choice for most machines; ensure you have enough RAM/VRAM + disk for the chosen quant. + +## Usage + +**Ollama** +```bash +ollama run hf.co/Shinzmann/naija-petro-GGUF:Q4_K_M +``` + +**llama.cpp** +```bash +./llama-cli -hf Shinzmann/naija-petro-GGUF:Q4_K_M \ + -p "What are the screening criteria for CO2 EOR?" -c 4096 +``` + +## License +Apache-2.0 (inherited from Qwen3-32B). Validate outputs with qualified engineers before operational use. diff --git a/config.json b/config.json new file mode 100644 index 0000000..8f0f8b5 --- /dev/null +++ b/config.json @@ -0,0 +1,100 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 25600, + "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", + "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": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": 151669, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "unsloth_version": "2026.3.7", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file