初始化项目，由ModelHub XC社区提供模型

Model: tletai/phi-4-mini-instruct-4b-usm-tau-py-0003 Source: Original Platform
2026-06-18 04:06:16 +08:00
commit 3c647f199b
12 changed files with 334 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,43 @@
+*.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
+phi-4-mini-instruct.Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/16
+++ b/16
@@ -0,0 +1,16 @@
+
+FROM phi-4-mini-instruct.F16.gguf
+TEMPLATE """{{- if or .System .Tools }}<|system|>{{ if .System }}{{ .System }}{{ end }}
+{{- if .Tools }}{{ if not .System }}You are a helpful assistant with some tools.{{ end }}<|tool|>{{ .Tools }}<|/tool|><|end|>
+{{- end }}
+{{- end }}
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 -}}
+{{- if ne .Role "system" }}<|{{ .Role }}|>{{ .Content }}
+{{- if .ToolCalls }}<|tool_call|>[{{ range .ToolCalls }}{"name":"{{ .Function.Name }}","arguments":{{ .Function.Arguments }}{{ end }}]<|/tool_call|>
+{{- end }}
+{{- if not $last }}<|end|>
+{{- end }}
+{{- if and (ne .Role "assistant") $last }}<|end|><|assistant|>{{ end }}
+{{- end }}
+{{- end }}"""
--- a/README.md
+++ b/README.md
@@ -0,0 +1,106 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+- ollama
+- phi4
+- phi-4
+- phi-4-mini
+- phi4mini
+- phi-4mini
+- 4b
+- python
+- code
+- coder
+- python-code
+- tlet-ai
+- tlet
+datasets:
+- iamtarun/python_code_instructions_18k_alpaca
+language:
+- en
+base_model:
+- unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit
+pipeline_tag: text-generation
+license: mit
+---
+
+# phi-4-mini-instruct-4b-usm-tau-py-0003 (GGUF)
+
+<center><img src="https://cdn-uploads.huggingface.co/production/uploads/695d0e4f802fc1b162e79766/wahq-sptk6-jyXU2KLh-h.png" width="600px"/></center>
+
+## Internal Model Name: Tau0-Py-003-4B-ir
+
+**Explaining how TLET AI public & internal model names work:**
+- Public Model Name: **{basemodel}**-**{parameters}**-**{type}**-**{series}**-**{hyperspecialization (when USM type)}**-**{release type number}{versioning number (digits are 3x what release type number digits are)}**
+- So: **phi-4-mini-instruct-4b-usm-tau-py-0003** means:
+- - **Base:** phi-4-mini-instruct (specifically [unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit))
+  - **Parameters:** 4 Billion
+  - **Type:** USM (Ultra Specialized Model)
+  - **Series:** Tau (Proof of Concept model series)
+  - **Hyperspecialization (is USM):** Python
+  - **Release Type:** 0, Proof of Concept/Early Works stage
+  - **Release Version:** 003, this is the 3rd model in the Tau series of models (includes fine-tunes that come from other base models.)
+- Internal/Private Model Name: **{series}{release type number}**-**{hyperspecialization}**-**{versioning number (digits are 3x what release type number digits are)}**-**{parameters}**-**{ir IF model is Inference Ready (Ollama)}**
+- So: **Tau0-Py-003-4B-ir** means:
+- - **Series:** Tau (Proof of Concept model series)
+  - **Release Type:** 0, Proof of Concept/Early Works stage
+  - **Hyperspecialization (is USM):** Python
+  - **Release Version:** 003, this is the 3rd model in the Tau series of models (includes fine-tunes that come from other base models.)
+  - **Is inference ready.**
+
+## Ollama Commands (with recommended Q5_K_M quantization)
+### Pull
+```
+ollama pull hf.co/tletai/phi-4-mini-instruct-4b-usm-tau-py-0003:Q5_K_M
+```
+### Run Command
+```
+ollama run hf.co/tletai/phi-4-mini-instruct-4b-usm-tau-py-0003:Q5_K_M
+```
+
+### Aliasing
+While you are running it, you can run the following command to save it with it's much simpler internal name for ease of use via Ollama. (This command should be ran AFTER running `ollama run`, meaning, when you are already chatting with the model in the CLI.)
+
+```
+>>> /save tau0-py-003-4B-ir:Q5_K_M
+```
+
+This will allow you to run it using this command instead:
+```
+ollama run tau0-py-003-4B-ir:Q5_K_M
+```
+
+You can remove parts you don't want, such as "-4B-ir" or ":Q5_K_M" (which isn't really needed if you're just planning on downloading a single quantization anyways) from the /save command as you wish.
+
+### Deleting Aliases
+This command will remove the alias **but keep the model**:
+```
+ollama rm tau0-py-003-4B-ir:Q5_K_M
+```
+
+### Complete Deletion
+To fully remove the model, remove all aliases and also remove the original pull:
+```
+ollama rm hf.co/tletai/phi-4-mini-instruct-4b-usm-tau-py-0003:Q5_K_M
+```
+
+
+## Fine-tuning
+- Base model: [unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit)
+- Done using **QLoRA**, **Paged AdamW 32-bit** with an **8K Context Length** on an **NVidia RTX 3060 Ti (8GB VRAM)** for **6h47m** at about **~112W** power draw for most of the time, with occassional hike-ups to at-most **217W** (of therotical possible 225W.)
+- Tokens during training: **4699303**.
+- Epochs completed: **1.33** (67% of 2 target epochs, runtime got too long for proof of concept, so it was cancelled. Steps for more precise, in our config: 3099/4654.)
+- Done using [**Unsloth Studio**](https://unsloth.ai/docs/new/studio), which largely increased training efficency and speed. 
+- If you need specifics for research purposes, possible collaboration, fine-tuning a model yourself or are just curious, feel free to reach out. **We do not have specific, timed power usage data anymore. It was discarded immediately after it was used, do not ask for it.**
+
+### System Specifications
+- `CPU` `1x` i9-12900KF
+- `RAM` `4x` 16GB of RAM (DDR4, 3600MHz)
+- - `TOTAL` 64GB of RAM (DDR4, 3600MHz)
+- `GPUS`
+- - `1x` NVIDIA GeForce RTX 3060 Ti (8GB of VRAM)
+- `OS` Windows 10 Native
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
--- a/config.json
+++ b/config.json
@@ -0,0 +1,145 @@
+{
+    "architectures": [
+        "Phi3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_phi3.Phi3Config",
+        "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM",
+        "AutoTokenizer": "Xenova/gpt-4o"
+    },
+    "bos_token_id": 199999,
+    "torch_dtype": "bfloat16",
+    "embd_pdrop": 0.0,
+    "eos_token_id": 200020,
+    "full_attn_mod": 1,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8192,
+    "interpolate_factor": 1,
+    "lm_head_bias": false,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_name": "unsloth/Phi-4-mini-instruct-unsloth-bnb-4bit",
+    "model_type": "phi3",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "original_max_position_embeddings": 4096,
+    "pad_token_id": 200029,
+    "partial_rotary_factor": 0.75,
+    "resid_pdrop": 0.0,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "long_factor": [
+            1,
+            1.118320672,
+            1.250641126,
+            1.398617824,
+            1.564103225,
+            1.74916897,
+            1.956131817,
+            2.187582649,
+            2.446418898,
+            2.735880826,
+            3.059592084,
+            3.421605075,
+            3.826451687,
+            4.279200023,
+            4.785517845,
+            5.351743533,
+            5.984965424,
+            6.693110555,
+            7.485043894,
+            8.370679318,
+            9.36110372,
+            10.4687158,
+            11.70738129,
+            13.09260651,
+            14.64173252,
+            16.37415215,
+            18.31155283,
+            20.47818807,
+            22.90118105,
+            25.61086418,
+            28.64115884,
+            32.03,
+            32.1,
+            32.13,
+            32.23,
+            32.6,
+            32.61,
+            32.64,
+            32.66,
+            32.7,
+            32.71,
+            32.93,
+            32.97,
+            33.28,
+            33.49,
+            33.5,
+            44.16,
+            47.77
+        ],
+        "short_factor": [
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0,
+            1.0
+        ],
+        "type": "longrope"
+    },
+    "rope_theta": 10000.0,
+    "sliding_window": 262144,
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.8",
+    "use_cache": true,
+    "vocab_size": 200064
+}
--- a/phi-4-mini-instruct.BF16.gguf
+++ b/phi-4-mini-instruct.BF16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af62b97435c0cd98e780ef1c93827b8b5bcea7a69fef30e6c1cab72cc2cad2b4
+size 7680694176
--- a/phi-4-mini-instruct.F16.gguf
+++ b/phi-4-mini-instruct.F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddf05202b179a6fcd1181955b73f689f792ce89fabc93060dd81e634a8def12
+size 7680694176
--- a/phi-4-mini-instruct.Q2_K_L.gguf
+++ b/phi-4-mini-instruct.Q2_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f41475a00e29361a638d11e8c73a659f55f73fdb8e3f76778b61722bdced9d
+size 1882601376
--- a/phi-4-mini-instruct.Q3_K_M.gguf
+++ b/phi-4-mini-instruct.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd34975bdbe3727e62b3002b8aa0f092c80bdb70861d9e4f563250e83daceb52
+size 2121464736
--- a/phi-4-mini-instruct.Q4_K_M.gguf
+++ b/phi-4-mini-instruct.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafc5e48f682deca87a099e991cef18a2d0b3090767d0d7cce9df092ee571fcd
+size 2493840288
--- a/phi-4-mini-instruct.Q5_K_M.gguf
+++ b/phi-4-mini-instruct.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2fb1eaaf885048689cbfea51b566cca8ab2d05854a4ad63507e79697c77ff2
+size 2814704544
--- a/phi-4-mini-instruct.Q6_K.gguf
+++ b/phi-4-mini-instruct.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53ca0c4d74c98e3dd4e5ff15c0a16f5e6d812342e6d73c2fbddf13ab5231fa1e
+size 3155622816
--- a/phi-4-mini-instruct.Q8_0.gguf
+++ b/phi-4-mini-instruct.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22169f2477b49041b1998ec5fd2338ae5c788b9253b229a5421328b3fd391af3
+size 4084610976