初始化项目，由ModelHub XC社区提供模型
Model: jhu-clsp/rank1-llama3-8b Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
180
README.md
Normal file
180
README.md
Normal file
@@ -0,0 +1,180 @@
|
||||
---
|
||||
license: mit
|
||||
datasets:
|
||||
- jhu-clsp/rank1-training-data
|
||||
base_model:
|
||||
- meta-llama/Llama-3.1-8B
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- reranker
|
||||
- retrieval
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
# rank1-llama3-8b: Test-Time Compute for Reranking in Information Retrieval
|
||||
|
||||
📄 [Paper](https://arxiv.org/abs/2502.18418) | 🚀 [GitHub Repository](https://github.com/orionw/rank1)
|
||||
|
||||
rank1 is a reasoning reranker model that "thinks" before making relevance judgments. This 8B parameter model is trained from the Llama 3.1 8B base model and leverages test-time compute to generate reasoning chains before deciding if a document is relevant to a query.
|
||||
|
||||
## Model Description
|
||||
|
||||
rank1 introduces a novel approach to information retrieval by generating explicit reasoning chains before making relevance judgments. Unlike traditional rerankers that directly output scores, rank1:
|
||||
|
||||
1. Receives a query and document pair
|
||||
2. Generates a reasoning chain within a `<think>...</think>` section
|
||||
3. Makes a binary relevance judgment (`true` or `false`)
|
||||
4. Returns a confidence score based on the logits of the true/false tokens
|
||||
|
||||
This approach helps the model break down complex relevance decisions into logical steps, improving performance across diverse retrieval tasks.
|
||||
|
||||
## Model Family
|
||||
|
||||
| Model | Base | Description |
|
||||
|:------|:-----|:------------|
|
||||
| [rank1-7b](https://huggingface.co/jhu-clsp/rank1-7b) | Qwen2.5-7B | Qwen variant (7B parameters) |
|
||||
| [rank1-14b](https://huggingface.co/jhu-clsp/rank1-14b) | Qwen2.5-14B | Qwen variant (14B parameters) |
|
||||
| [rank1-32b](https://huggingface.co/jhu-clsp/rank1-32b) | Qwen2.5-32B | Qwen variant (32B parameters) |
|
||||
| [rank1-mistral-2501-24b](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b) | Mistral-Small 2501 24B | Mistral variant (24B parameters) |
|
||||
| [rank1-llama3-8b](https://huggingface.co/jhu-clsp/rank1-llama3-8b) | Llama 3.1 8B | Current model (8B parameters) |
|
||||
|
||||
### Quantized Variants
|
||||
|
||||
| Model | Description |
|
||||
|:------|:------------|
|
||||
| [rank1-7b-awq](https://huggingface.co/jhu-clsp/rank1-7b-awq) | Quantized version of rank1-7b |
|
||||
| [rank1-14b-awq](https://huggingface.co/jhu-clsp/rank1-14b-awq) | Quantized version of rank1-14b |
|
||||
| [rank1-32b-awq](https://huggingface.co/jhu-clsp/rank1-32b-awq) | Quantized version of rank1-32b |
|
||||
| [rank1-mistral-2501-24b-awq](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b-awq) | Quantized version of rank1-mistral-24b |
|
||||
| [rank1-llama3-8b-awq](https://huggingface.co/jhu-clsp/rank1-llama3-8b-awq) | Quantized version of rank1-llama3-8b |
|
||||
|
||||
## Associated Data and Resources
|
||||
|
||||
| Resource | Description |
|
||||
|:---------|:------------|
|
||||
| [rank1-r1-msmarco](https://huggingface.co/datasets/jhu-clsp/rank1-r1-msmarco) | All R1 output examples from MS MARCO |
|
||||
| [rank1-training-data](https://huggingface.co/datasets/jhu-clsp/rank1-training-data) | Training data used for rank1 models |
|
||||
| [rank1-run-files](https://huggingface.co/datasets/jhu-clsp/rank1-run-files) | Pre-computed run files for use in top 100 doc reranking |
|
||||
| [GitHub Repository](https://github.com/orionw/rank1) | Official rank1 repository |
|
||||
|
||||
## Usage
|
||||
Note that official usage is found on the Github and accounts for edge cases. But for simple use cases the minimal example below works.
|
||||
|
||||
<details>
|
||||
<summary>Click to expand: Minimal example with vLLM</summary>
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
import math
|
||||
|
||||
# Initialize the model with vLLM
|
||||
model = LLM(
|
||||
model="jhu-clsp/rank1-llama3-8b",
|
||||
tensor_parallel_size=1, # Number of GPUs
|
||||
trust_remote_code=True,
|
||||
max_model_len=16000, # Context length
|
||||
gpu_memory_utilization=0.9,
|
||||
dtype="float16",
|
||||
)
|
||||
|
||||
# Set up sampling parameters
|
||||
sampling_params = SamplingParams(
|
||||
temperature=0,
|
||||
max_tokens=8192,
|
||||
logprobs=20,
|
||||
stop=["</think> true", "</think> false"],
|
||||
skip_special_tokens=False
|
||||
)
|
||||
|
||||
# Prepare the prompt
|
||||
def create_prompt(query, document):
|
||||
return (
|
||||
"Determine if the following passage is relevant to the query. "
|
||||
"Answer only with 'true' or 'false'.\n"
|
||||
f"Query: {query}\n"
|
||||
f"Passage: {document}\n"
|
||||
"<think>"
|
||||
)
|
||||
|
||||
# Example usage
|
||||
query = "What are the effects of climate change?"
|
||||
document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities."
|
||||
|
||||
# Generate prediction
|
||||
prompt = create_prompt(query, document)
|
||||
outputs = model.generate([prompt], sampling_params)
|
||||
|
||||
# Extract score
|
||||
output = outputs[0].outputs[0]
|
||||
text = output.text
|
||||
final_logits = output.logprobs[-1]
|
||||
|
||||
# Get token IDs for "true" and "false" tokens
|
||||
from transformers import AutoTokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-llama3-8b")
|
||||
true_token = tokenizer(" true", add_special_tokens=False).input_ids[0]
|
||||
false_token = tokenizer(" false", add_special_tokens=False).input_ids[0]
|
||||
|
||||
# Calculate relevance score (probability of "true")
|
||||
true_logit = final_logits[true_token].logprob
|
||||
false_logit = final_logits[false_token].logprob
|
||||
true_score = math.exp(true_logit)
|
||||
false_score = math.exp(false_logit)
|
||||
relevance_score = true_score / (true_score + false_score)
|
||||
|
||||
print(f"Reasoning chain: {text}")
|
||||
print(f"Relevance score: {relevance_score}")
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
## Performance
|
||||
|
||||
rank1-llama3-8b demonstrates strong performance on retrieval benchmarks, particularly on tasks requiring complex reasoning. The model's ability to "think through" relevance decisions makes it especially effective for nuanced topics.
|
||||
|
||||
For specific benchmark results and comparisons with other models, please refer to the paper and the official GitHub repository.
|
||||
|
||||
## Installation
|
||||
|
||||
Please see the Github for detailed installation instructions.
|
||||
|
||||
## MTEB Integration
|
||||
|
||||
rank1 is compatible with the [MTEB benchmarking framework](https://github.com/embeddings-benchmark/mteb):
|
||||
|
||||
```python
|
||||
from mteb import MTEB
|
||||
from rank1 import rank1 # From the official repo
|
||||
|
||||
# Initialize the model
|
||||
model = rank1(
|
||||
model_name_or_path="jhu-clsp/rank1-llama3-8b",
|
||||
num_gpus=1,
|
||||
device="cuda"
|
||||
)
|
||||
|
||||
# Run evaluation on specific tasks
|
||||
evaluation = MTEB(tasks=["NevIR"])
|
||||
results = evaluation.run(model)
|
||||
```
|
||||
|
||||
## Citation
|
||||
|
||||
If you use rank1 in your research, please cite our work:
|
||||
|
||||
```bibtex
|
||||
@misc{weller2025rank1testtimecomputereranking,
|
||||
title={Rank1: Test-Time Compute for Reranking in Information Retrieval},
|
||||
author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme},
|
||||
year={2025},
|
||||
eprint={2502.18418},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.IR},
|
||||
url={https://arxiv.org/abs/2502.18418},
|
||||
}
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
[MIT License](https://github.com/orionw/rank1/blob/main/LICENSE)
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 8192,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.48.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128320
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
9
generation_config.json
Normal file
9
generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"max_length": 4096,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.48.2"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d0ce6f78fd91d21b4ed3c83c858e9a72dbfe655343e173854e9954efdaee27aa
|
||||
size 9977025688
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:91f9dda537874e8a5fae4590f9f7a74129025835333af9ec66756b7455df1d3a
|
||||
size 6084579288
|
||||
298
model.safetensors.index.json
Normal file
298
model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16061571072
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00002-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
{
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
{
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|end_of_text|>"
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0eb85735b2f18c464a3a3854c1f6e06f0c2cee200359d38ccd3e4667c947cdc0
|
||||
size 17210330
|
||||
2086
tokenizer_config.json
Normal file
2086
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user