初始化项目，由ModelHub XC社区提供模型
Model: AvoCahDoe/llama-2-7b-rlmpq-balanced Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
89
README.md
Normal file
89
README.md
Normal file
@@ -0,0 +1,89 @@
|
||||
---
|
||||
license: llama2
|
||||
base_model: meta-llama/Llama-2-7b-hf
|
||||
pipeline_tag: text-generation
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- llama
|
||||
- text-generation
|
||||
- rl-mpq
|
||||
- mixed-precision
|
||||
- quantization
|
||||
- fake-quantization
|
||||
- balanced
|
||||
- llama-2
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- wikitext
|
||||
widget:
|
||||
- text: "The capital of France is"
|
||||
---
|
||||
|
||||
# Llama 2 7B — RL-MPQ Balanced
|
||||
|
||||
Standalone **RL-MPQ** (Reinforcement Learning Mixed-Precision Quantization) checkpoint for the
|
||||
**Balanced** scenario — a quantized variant of
|
||||
[meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf).
|
||||
|
||||
| Field | Value |
|
||||
|-------|-------|
|
||||
| **Base model** | [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) |
|
||||
| **Scenario** | Balanced |
|
||||
| **Avg bits / weight** | 4.375 |
|
||||
| **Compression vs FP16** | 3.6571× |
|
||||
| **WikiText-2 PPL** | 5.0437 |
|
||||
| **Layers** | 32 |
|
||||
| **Bit distribution** | `{'4': 29, '8': 3}` |
|
||||
| **Format** | Fake-quant FP16 + `rlmpq_policy.json` |
|
||||
|
||||
**Collection:** [RL-MPQ — Llama 2 7B](https://huggingface.co/collections/AvoCahDoe/rl-mpq-llama-2-7b-6a2ae4f8c590727304e3f634) — all five scenarios for Llama 2 7B.
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
repo = "AvoCahDoe/llama-2-7b-rlmpq-balanced"
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="float16")
|
||||
tokenizer = AutoTokenizer.from_pretrained(repo)
|
||||
```
|
||||
|
||||
## Other Llama 2 7B scenarios
|
||||
|
||||
| Scenario | Avg bits | Compression | WikiText-2 PPL |
|
||||
|----------|----------|-------------|----------------|
|
||||
| [High Fidelity](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq-high-fidelity) | 6.5 | 2.4615x | 4.9808 |
|
||||
| [Conservative](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq-conservative) | 5.125 | 3.122x | 5.0276 |
|
||||
| [Aggressive](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq-aggressive) | 3.5938 | 4.4522x | 5.2614 |
|
||||
| [Extreme Survival](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq-extreme-survival) | 2.9688 | 5.3895x | 10.9577 |
|
||||
|
||||
Grouped archive (all scenarios in one repo):
|
||||
[AvoCahDoe/llama-2-7b-rlmpq](https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq)
|
||||
|
||||
## Method
|
||||
|
||||
1. **Phase 3** — PPO agent assigns per-layer bit widths under the Balanced reward target.
|
||||
2. **Phase 4** — Policy replayed on real weights; WikiText-2 perplexity validates quality.
|
||||
3. **Export** — Fake-quantized FP16 weights compatible with Hugging Face Transformers.
|
||||
|
||||
## Files
|
||||
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| `config.json` | Llama architecture + RL-MPQ metadata |
|
||||
| `model.safetensors` | Fake-quantized weights |
|
||||
| `rlmpq_policy.json` | Per-layer bit-width policy |
|
||||
| `rlmpq_metrics.json` | Validation & PPL summary |
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{rlmpq_llama_2_7b_balanced_2026,
|
||||
title = {RL-MPQ Balanced: Llama 2 7B Mixed-Precision Quantization},
|
||||
author = {AvoCahDoe},
|
||||
year = {2026},
|
||||
url = {https://huggingface.co/AvoCahDoe/llama-2-7b-rlmpq-balanced}
|
||||
}
|
||||
```
|
||||
49
config.json
Normal file
49
config.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"pad_token_id": null,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default",
|
||||
"type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.11.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000,
|
||||
"base_model": "meta-llama/Llama-2-7b-hf",
|
||||
"quantization": {
|
||||
"method": "rl-mpq",
|
||||
"format": "fake-quant-fp16",
|
||||
"scenario": "Balanced",
|
||||
"avg_bits": 4.375,
|
||||
"description": "Per-layer mixed bit-width via PPO-trained policy (not GPTQ/AWQ)"
|
||||
},
|
||||
"rlmpq": {
|
||||
"framework": "RL-NMP-Model-Quantasation",
|
||||
"scenario": "Balanced",
|
||||
"scenario_label": "Balanced",
|
||||
"repo_id": "AvoCahDoe/llama-2-7b-rlmpq-balanced",
|
||||
"grouped_repo": "AvoCahDoe/llama-2-7b-rlmpq",
|
||||
"collection_title": "RL-MPQ \u2014 Llama 2 7B"
|
||||
}
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 4096,
|
||||
"pad_token_id": 0,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "5.11.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e825c624ea11056bef28bdb62d44a6b458b45260533539fdde154ddfcdf46132
|
||||
size 13476864944
|
||||
23
rlmpq_metrics.json
Normal file
23
rlmpq_metrics.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"framework": "RL-NMP-Model-Quantasation",
|
||||
"method": "RL-MPQ",
|
||||
"repo_id": "AvoCahDoe/llama-2-7b-rlmpq-balanced",
|
||||
"base_model": "meta-llama/Llama-2-7b-hf",
|
||||
"model_slug": "llama_2_7b",
|
||||
"scenario": "Balanced",
|
||||
"scenario_label": "Balanced",
|
||||
"avg_bits_per_weight": 4.375,
|
||||
"compression_vs_fp16": 3.6571,
|
||||
"wikitext2_perplexity": 5.0437,
|
||||
"bit_distribution": {
|
||||
"4": 29,
|
||||
"8": 3
|
||||
},
|
||||
"quantization": {
|
||||
"type": "fake-quant-fp16",
|
||||
"group_size": 128,
|
||||
"scheme": "per-layer asymmetric group-wise",
|
||||
"packed_format": false
|
||||
},
|
||||
"exported_at": "2026-06-11T16:40:33.183918"
|
||||
}
|
||||
60
rlmpq_policy.json
Normal file
60
rlmpq_policy.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"slug": "llama_2_7b",
|
||||
"hf_id": "meta-llama/Llama-2-7b-hf",
|
||||
"scenario": "Balanced",
|
||||
"params": {
|
||||
"lambda_mse": 1.0,
|
||||
"lambda_bit": 0.25,
|
||||
"max_mse_clip": 1.0,
|
||||
"target_bits": 4.5,
|
||||
"lambda_budget": 5.0
|
||||
},
|
||||
"policy": [
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
4,
|
||||
8,
|
||||
8,
|
||||
8
|
||||
],
|
||||
"num_layers": 32,
|
||||
"avg_bits": 4.375,
|
||||
"total_reward": -4.832758,
|
||||
"compression_ratio": 3.6571,
|
||||
"approx_size_gb": 3.828,
|
||||
"bit_distribution": {
|
||||
"4": 29,
|
||||
"8": 3
|
||||
},
|
||||
"avg_mse_per_bit": {
|
||||
"4": 0.28526766,
|
||||
"8": 3.942e-05
|
||||
},
|
||||
"validation_elapsed_s": 0.0583
|
||||
}
|
||||
277129
tokenizer.json
Normal file
277129
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user