Add files using upload-large-folder tool
Browse files- .gitattributes +6 -0
- Phi-4-reasoning-plus-UD-IQ1_M.gguf +3 -0
- Phi-4-reasoning-plus-UD-IQ1_S.gguf +3 -0
- Phi-4-reasoning-plus-UD-IQ2_M.gguf +3 -0
- Phi-4-reasoning-plus-UD-IQ3_XXS.gguf +3 -0
- Phi-4-reasoning-plus-UD-Q2_K_XL.gguf +3 -0
- Phi-4-reasoning-plus-UD-Q4_K_XL.gguf +3 -0
- README.md +16 -48
- config.json +33 -0
.gitattributes
CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Phi-4-reasoning-plus-UD-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Phi-4-reasoning-plus-UD-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Phi-4-reasoning-plus-UD-Q2_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Phi-4-reasoning-plus-UD-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Phi-4-reasoning-plus-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Phi-4-reasoning-plus-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
Phi-4-reasoning-plus-UD-IQ1_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:624c8679b40c3eaf7164f99c02e6c946861550ee3df92b9b596324937f942c26
|
3 |
+
size 3831085088
|
Phi-4-reasoning-plus-UD-IQ1_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f889c78bffd03a7976e78d074636094df1bad820d4e072dd229b522c732a4d
|
3 |
+
size 3580205088
|
Phi-4-reasoning-plus-UD-IQ2_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39d25ca38aa382b6185435bd54d815a43e027188c2b8d58da84c0090ed81341a
|
3 |
+
size 5257619488
|
Phi-4-reasoning-plus-UD-IQ3_XXS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79de820a4275d88c3c025b06696eda72d0816d5d5256a165607261858b9b998a
|
3 |
+
size 5890861088
|
Phi-4-reasoning-plus-UD-Q2_K_XL.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8842533bcbc1fda4ecc70336068ad73e6ab655127d62831034a01cd88092d997
|
3 |
+
size 5803452448
|
Phi-4-reasoning-plus-UD-Q4_K_XL.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6053d64bc55e3d04ab4a5ec50f939f2d359295a3090f31b3818aea65c6d4b54
|
3 |
+
size 8947337248
|
README.md
CHANGED
@@ -1,63 +1,31 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
-
- microsoft/Phi-4-reasoning-plus
|
4 |
-
language:
|
5 |
-
- en
|
6 |
-
library_name: transformers
|
7 |
license: mit
|
8 |
license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE
|
|
|
|
|
|
|
|
|
9 |
pipeline_tag: text-generation
|
10 |
tags:
|
11 |
-
-
|
12 |
- unsloth
|
|
|
13 |
- math
|
14 |
- code
|
15 |
-
-
|
16 |
-
-
|
|
|
|
|
|
|
|
|
17 |
widget:
|
18 |
- messages:
|
19 |
- role: user
|
20 |
-
content:
|
|
|
21 |
---
|
22 |
-
|
23 |
-
|
24 |
-
>
|
25 |
-
<div>
|
26 |
-
<p style="margin-bottom: 0; margin-top: 0;">
|
27 |
-
<strong>See <a href="https://huggingface.co/collections/unsloth/phi-4-all-versions-677eecf93784e61afe762afa">our collection</a> for all versions of Phi-4 including GGUF, 4-bit & 16-bit formats.</strong>
|
28 |
-
</p>
|
29 |
-
<p style="margin-top: 0;margin-bottom: 0;">
|
30 |
-
<em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
31 |
-
</p>
|
32 |
-
<div style="display: flex; gap: 5px; align-items: center; ">
|
33 |
-
<a href="https://github.com/unslothai/unsloth/">
|
34 |
-
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
35 |
-
</a>
|
36 |
-
<a href="https://discord.gg/unsloth">
|
37 |
-
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
38 |
-
</a>
|
39 |
-
<a href="https://docs.unsloth.ai/">
|
40 |
-
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
41 |
-
</a>
|
42 |
-
</div>
|
43 |
-
<h1 style="margin-top: 0rem;">✨ Run & Fine-tune Phi-4 with Unsloth!</h1>
|
44 |
-
</div>
|
45 |
-
|
46 |
-
- Fine-tune Phi-4 (14B) for free using our Google [Colab notebook here](https://docs.unsloth.ai/get-started/unsloth-notebooks)!
|
47 |
-
- Read our Blog about Phi-4 support with our bug fixes: [unsloth.ai/blog/phi4](https://unsloth.ai/blog/phi4)
|
48 |
-
- View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks).
|
49 |
-
- Run & export your fine-tuned model to Ollama, llama.cpp or HF.
|
50 |
-
|
51 |
-
| Unsloth supports | Free Notebooks | Performance | Memory use |
|
52 |
-
|-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
|
53 |
-
| **Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4-Conversational.ipynb) | 2x faster | 50% less |
|
54 |
-
| **Qwen3 (14B)** | [▶️ Start on Colab](https://docs.unsloth.ai/get-started/unsloth-notebooks) | 3x faster | 70% less |
|
55 |
-
| **GRPO with Phi-4 (14B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Phi_4_(14B)-GRPO.ipynb) | 3x faster | 80% less |
|
56 |
-
| **Llama-3.2 (3B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(1B_and_3B)-Conversational.ipynb) | 2x faster | 80% less |
|
57 |
-
| **Llama-3.2 (11B vision)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.2_(11B)-Vision.ipynb) | 2x faster | 60% less |
|
58 |
-
| **Qwen2.5 (7B)** | [▶️ Start on Colab](https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Qwen2.5_(7B)-Alpaca.ipynb) | 2x faster | 60% less |
|
59 |
-
|
60 |
-
# Phi-4-reasoning-plus
|
61 |
|
62 |
[Phi-4-reasoning Technical Report](https://aka.ms/phi-reasoning/techreport)
|
63 |
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
2 |
license: mit
|
3 |
license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus/resolve/main/LICENSE
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
base_model:
|
7 |
+
- microsoft/Phi-4-reasoning-plus
|
8 |
pipeline_tag: text-generation
|
9 |
tags:
|
10 |
+
- phi
|
11 |
- unsloth
|
12 |
+
- nlp
|
13 |
- math
|
14 |
- code
|
15 |
+
- chat
|
16 |
+
- conversational
|
17 |
+
- reasoning
|
18 |
+
inference:
|
19 |
+
parameters:
|
20 |
+
temperature: 0
|
21 |
widget:
|
22 |
- messages:
|
23 |
- role: user
|
24 |
+
content: What is the derivative of x^2?
|
25 |
+
library_name: transformers
|
26 |
---
|
27 |
+
|
28 |
+
# Phi-4-reasoning-plus Model Card
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
|
30 |
[Phi-4-reasoning Technical Report](https://aka.ms/phi-reasoning/techreport)
|
31 |
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Phi3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 100257,
|
8 |
+
"embd_pdrop": 0.0,
|
9 |
+
"eos_token_id": 100265,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 5120,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 17920,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "phi3",
|
16 |
+
"num_attention_heads": 40,
|
17 |
+
"num_hidden_layers": 40,
|
18 |
+
"num_key_value_heads": 10,
|
19 |
+
"original_max_position_embeddings": 32768,
|
20 |
+
"pad_token_id": 100349,
|
21 |
+
"partial_rotary_factor": 1.0,
|
22 |
+
"resid_pdrop": 0.0,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 500000,
|
26 |
+
"sliding_window": null,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.52.0.dev0",
|
30 |
+
"unsloth_fixed": true,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 100352
|
33 |
+
}
|