Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- README.md +26 -0
- config.json +64 -0
- functiongemma-vpc-f16.gguf +3 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ 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 |
+
functiongemma-vpc-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/functiongemma-270m-it
|
| 4 |
+
tags:
|
| 5 |
+
- function-calling
|
| 6 |
+
- vpc
|
| 7 |
+
- gguf
|
| 8 |
+
- q4_k_m
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# FunctionGemma-270M VPC — GGUF Q4_K_M
|
| 12 |
+
|
| 13 |
+
Fine-tuned for VPC & Routing tool-calling. Quantized to Q4_K_M GGUF for CPU inference.
|
| 14 |
+
|
| 15 |
+
## Install
|
| 16 |
+
```bash
|
| 17 |
+
pip install llama-cpp-python transformers sentencepiece
|
| 18 |
+
```
|
| 19 |
+
|
| 20 |
+
## Quick use
|
| 21 |
+
```python
|
| 22 |
+
from huggingface_hub import hf_hub_download
|
| 23 |
+
gguf_path = hf_hub_download(repo_id='madhuHuggingface/functiongemma-vpc-gguf', filename='functiongemma-vpc-q4_k_m.gguf')
|
| 24 |
+
```
|
| 25 |
+
|
| 26 |
+
See the companion `vpc_local_test.py` for the full 30-test evaluation.
|
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_sliding_window_pattern": 6,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Gemma3ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attn_logit_softcapping": null,
|
| 9 |
+
"bos_token_id": 2,
|
| 10 |
+
"torch_dtype": "float16",
|
| 11 |
+
"eos_token_id": 106,
|
| 12 |
+
"final_logit_softcapping": null,
|
| 13 |
+
"head_dim": 256,
|
| 14 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
| 15 |
+
"hidden_size": 640,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 2048,
|
| 18 |
+
"layer_types": [
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"sliding_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention"
|
| 37 |
+
],
|
| 38 |
+
"max_position_embeddings": 32768,
|
| 39 |
+
"model_name": "unsloth/functiongemma-270m-it",
|
| 40 |
+
"model_type": "gemma3_text",
|
| 41 |
+
"num_attention_heads": 4,
|
| 42 |
+
"num_hidden_layers": 18,
|
| 43 |
+
"num_key_value_heads": 1,
|
| 44 |
+
"pad_token_id": 0,
|
| 45 |
+
"query_pre_attn_scalar": 256,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"full_attention": {
|
| 49 |
+
"rope_theta": 1000000.0,
|
| 50 |
+
"rope_type": "default"
|
| 51 |
+
},
|
| 52 |
+
"sliding_attention": {
|
| 53 |
+
"rope_theta": 10000.0,
|
| 54 |
+
"rope_type": "default"
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"sliding_window": 512,
|
| 58 |
+
"tie_word_embeddings": true,
|
| 59 |
+
"unsloth_fixed": true,
|
| 60 |
+
"unsloth_version": "2026.5.2",
|
| 61 |
+
"use_bidirectional_attention": false,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 262144
|
| 64 |
+
}
|
functiongemma-vpc-f16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497ff27b2f177fbd4e37a080b1cf61de55d93836b57aec9dd05a96ba6b8d5a40
|
| 3 |
+
size 542847296
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
|
| 3 |
+
size 33384898
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
|
| 3 |
+
size 4689144
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|