初始化项目，由ModelHub XC社区提供模型
Model: ibm-granite/granite-20b-functioncalling Source: Original Platform
This commit is contained in:
ModelHub XC
44
.gitattributes
vendored
Normal file
44
.gitattributes
vendored
Normal file
@@ -0,0 +1,44 @@
|
||||
*.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
|
||||
model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
88
README.md
Normal file
88
README.md
Normal file
@@ -0,0 +1,88 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
### Granite-20B-FunctionCalling
|
||||
#### Model Summary
|
||||
Granite-20B-FunctionCalling is a finetuned model based on IBM's [granite-20b-code-instruct](https://huggingface.co/ibm-granite/granite-20b-code-instruct) model to introduce function calling abilities into Granite model family. The model is trained using a multi-task training approach on seven fundamental tasks encompassed in function calling, those being Nested Function Calling, Function Chaining, Parallel Functions, Function Name Detection, Parameter-Value Pair Detection, Next-Best Function, and Response Generation.
|
||||
|
||||
- **Developers**: IBM Research
|
||||
- **Paper**: [Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks](https://arxiv.org/pdf/2407.00121v1)
|
||||
- **Release Date**: July 9th, 2024
|
||||
- **License**: [Apache 2.0.](https://www.apache.org/licenses/LICENSE-2.0)
|
||||
|
||||
### Usage
|
||||
### Intended use
|
||||
The model is designed to respond to function calling related instructions.
|
||||
|
||||
### Generation
|
||||
This is a simple example of how to use Granite-20B-Code-FunctionCalling model.
|
||||
```python
|
||||
import json
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
device = "cuda" # or "cpu"
|
||||
model_path = "ibm-granite/granite-20b-functioncalling"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
||||
# drop device_map if running on CPU
|
||||
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
|
||||
model.eval()
|
||||
|
||||
# define the user query and list of available functions
|
||||
query = "What's the current weather in New York?"
|
||||
functions = [
|
||||
{
|
||||
"name": "get_current_weather",
|
||||
"description": "Get the current weather",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"location": {
|
||||
"type": "string",
|
||||
"description": "The city and state, e.g. San Francisco, CA"
|
||||
}
|
||||
},
|
||||
"required": ["location"]
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "get_stock_price",
|
||||
"description": "Retrieves the current stock price for a given ticker symbol. The ticker symbol must be a valid symbol for a publicly traded company on a major US stock exchange like NYSE or NASDAQ. The tool will return the latest trade price in USD. It should be used when the user asks about the current or most recent price of a specific stock. It will not provide any other information about the stock or company.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"ticker": {
|
||||
"type": "string",
|
||||
"description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
|
||||
}
|
||||
},
|
||||
"required": ["ticker"]
|
||||
}
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
# serialize functions and define a payload to generate the input template
|
||||
payload = {
|
||||
"functions_str": [json.dumps(x) for x in functions],
|
||||
"query": query,
|
||||
}
|
||||
|
||||
instruction = tokenizer.apply_chat_template(payload, tokenize=False, add_generation_prompt=True)
|
||||
|
||||
# tokenize the text
|
||||
input_tokens = tokenizer(instruction, return_tensors="pt").to(device)
|
||||
|
||||
# generate output tokens
|
||||
outputs = model.generate(**input_tokens, max_new_tokens=100)
|
||||
|
||||
# decode output tokens into text
|
||||
outputs = tokenizer.batch_decode(outputs)
|
||||
|
||||
# loop over the batch to print, in this example the batch size is 1
|
||||
for output in outputs:
|
||||
# Each function call in the output will be preceded by the token "<function_call>" followed by a
|
||||
# json serialized function call of the format {"name": $function_name$, "arguments" {$arg_name$: $arg_val$}}
|
||||
# In this specific case, the output will be: <function_call> {"name": "get_current_weather", "arguments": {"location": "New York"}}
|
||||
print(output)
|
||||
```
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"activation_function": "gelu_pytorch_tanh",
|
||||
"architectures": [
|
||||
"GPTBigCodeForCausalLM"
|
||||
],
|
||||
"attention_softmax_in_fp32": true,
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 0,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt_bigcode",
|
||||
"multi_query": true,
|
||||
"n_embd": 6144,
|
||||
"n_head": 48,
|
||||
"n_inner": 24576,
|
||||
"n_layer": 52,
|
||||
"n_positions": 8192,
|
||||
"pad_token_id": 0,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attention_softmax_in_fp32": true,
|
||||
"scale_attn_weights": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.41.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.41.2"
|
||||
}
|
||||
3
model-00001-of-00009.safetensors
Normal file
3
model-00001-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d78cd595b882f0972154cc6027cab3dfd578bcc49a59bb3f981645bcc58de6b9
|
||||
size 4952185256
|
||||
3
model-00002-of-00009.safetensors
Normal file
3
model-00002-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fec4bf61d20e06a33a6ff79b366d7984d1c1886e79709e8a69f553e6c4ae92ee
|
||||
size 4930227792
|
||||
3
model-00003-of-00009.safetensors
Normal file
3
model-00003-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eefb4ffc020004c0ddbef81aa058e3cdd9d7ea088843b525cebc7764e39ff8a5
|
||||
size 4927118464
|
||||
3
model-00004-of-00009.safetensors
Normal file
3
model-00004-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33e80095a19caf8825ab3984feca5d3d73c3ea5e9f8eea77f9deb7cd64a4272c
|
||||
size 4930227864
|
||||
3
model-00005-of-00009.safetensors
Normal file
3
model-00005-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9a131cb833d7fcd0e7e2a5d7822036b017f33c895f062fb446cc059329cec24f
|
||||
size 4927118464
|
||||
3
model-00006-of-00009.safetensors
Normal file
3
model-00006-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3be57f692125c4d421d652a321d187079d28c0a23aa8b71e77cd0cc704b0ea7
|
||||
size 4930227864
|
||||
3
model-00007-of-00009.safetensors
Normal file
3
model-00007-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:216ed1f8d3191cd44871e85dbf544b5dcd2e5ad96a1caa8e7027ebd0cf92bb1b
|
||||
size 4927118464
|
||||
3
model-00008-of-00009.safetensors
Normal file
3
model-00008-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b97ec2a8ec14d3fd8af72ea768e9edb0e490dc77945554a1d4c7b78a7e0792b
|
||||
size 4930227864
|
||||
3
model-00009-of-00009.safetensors
Normal file
3
model-00009-of-00009.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c6e4520259c91595c44c3b4daa1bf4a2b41fa08a0fb47cae5dc765e1ac1d9cb
|
||||
size 679601176
|
||||
635
model.safetensors.index.json
Normal file
635
model.safetensors.index.json
Normal file
@@ -0,0 +1,635 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 40133986304
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.0.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.1.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.10.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.10.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.11.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.12.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.12.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.12.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.12.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.12.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.12.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.13.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.14.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.15.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.16.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.17.mlp.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.attn.c_attn.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.attn.c_attn.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.attn.c_proj.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.attn.c_proj.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.ln_1.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.ln_1.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.ln_2.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.ln_2.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.bias": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.mlp.c_fc.weight": "model-00003-of-00009.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.18.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.19.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.2.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.2.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.20.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.20.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.21.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.22.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.23.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.attn.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.attn.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.ln_2.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.ln_2.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.mlp.c_fc.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.24.mlp.c_proj.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.25.attn.c_attn.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.25.attn.c_attn.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.25.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.ln_1.bias": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.25.ln_1.weight": "model-00004-of-00009.safetensors",
|
||||
"transformer.h.25.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.25.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.26.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.27.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.28.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.29.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.3.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.3.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.30.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.30.mlp.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.attn.c_attn.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.attn.c_attn.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.attn.c_proj.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.attn.c_proj.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.ln_1.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.ln_1.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.ln_2.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.ln_2.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.bias": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.mlp.c_fc.weight": "model-00005-of-00009.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.31.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.32.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.33.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.34.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.35.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.36.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.attn.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.attn.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.ln_2.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.ln_2.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.mlp.c_fc.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.mlp.c_fc.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.mlp.c_proj.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.37.mlp.c_proj.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.38.attn.c_attn.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.38.attn.c_attn.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.38.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.ln_1.bias": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.38.ln_1.weight": "model-00006-of-00009.safetensors",
|
||||
"transformer.h.38.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.38.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.39.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.4.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.4.mlp.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.40.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.40.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.41.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.42.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.mlp.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.43.mlp.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.attn.c_attn.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.attn.c_attn.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.attn.c_proj.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.attn.c_proj.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.ln_1.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.ln_1.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.ln_2.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.ln_2.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.mlp.c_fc.bias": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.mlp.c_fc.weight": "model-00007-of-00009.safetensors",
|
||||
"transformer.h.44.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.44.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.45.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.46.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.47.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.48.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.49.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.5.attn.c_attn.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.attn.c_attn.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.attn.c_proj.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.attn.c_proj.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.ln_1.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.ln_1.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.ln_2.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.ln_2.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.bias": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.mlp.c_fc.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.5.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.50.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.attn.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.attn.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.ln_2.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.ln_2.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.mlp.c_fc.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.mlp.c_fc.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.mlp.c_proj.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.50.mlp.c_proj.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.51.attn.c_attn.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.51.attn.c_attn.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.51.attn.c_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.attn.c_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.ln_1.bias": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.51.ln_1.weight": "model-00008-of-00009.safetensors",
|
||||
"transformer.h.51.ln_2.bias": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.ln_2.weight": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.mlp.c_fc.bias": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.mlp.c_fc.weight": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.mlp.c_proj.bias": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.51.mlp.c_proj.weight": "model-00009-of-00009.safetensors",
|
||||
"transformer.h.6.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.6.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.7.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.8.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.attn.c_attn.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.attn.c_attn.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.attn.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.attn.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.ln_1.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.ln_1.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.ln_2.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.ln_2.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.mlp.c_fc.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.bias": "model-00002-of-00009.safetensors",
|
||||
"transformer.h.9.mlp.c_proj.weight": "model-00002-of-00009.safetensors",
|
||||
"transformer.ln_f.bias": "model-00009-of-00009.safetensors",
|
||||
"transformer.ln_f.weight": "model-00009-of-00009.safetensors",
|
||||
"transformer.wpe.weight": "model-00001-of-00009.safetensors",
|
||||
"transformer.wte.weight": "model-00001-of-00009.safetensors"
|
||||
}
|
||||
}
|
||||
51
special_tokens_map.json
Normal file
51
special_tokens_map.json
Normal file
@@ -0,0 +1,51 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<fim_prefix>",
|
||||
"<fim_middle>",
|
||||
"<fim_suffix>",
|
||||
"<fim_pad>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<empty_output>",
|
||||
"<commit_before>",
|
||||
"<commit_msg>",
|
||||
"<commit_after>",
|
||||
"<reponame>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
98258
tokenizer.json
Normal file
98258
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
188
tokenizer_config.json
Normal file
188
tokenizer_config.json
Normal file
@@ -0,0 +1,188 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<fim_prefix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<fim_middle>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<fim_suffix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<fim_pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "<commit_before>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "<commit_msg>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"17": {
|
||||
"content": "<commit_after>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"18": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<fim_prefix>",
|
||||
"<fim_middle>",
|
||||
"<fim_suffix>",
|
||||
"<fim_pad>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<empty_output>",
|
||||
"<commit_before>",
|
||||
"<commit_msg>",
|
||||
"<commit_after>",
|
||||
"<reponame>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"chat_template": "{% set function_str = messages.get('functions_str', {}) %}\n{% set query = messages['query'] %}\n{% set sys_prompt = 'You are a helpful assistant with access to the following function calls. Your task is to produce a sequence of function calls necessary to generate response to the user utterance. Use the following function calls as required. ' %}\n{% set funcstr = function_str|join('\n') %}\n{{ 'SYSTEM: ' + sys_prompt + '\n<|function_call_library|>\n' + funcstr + '\n\nIf none of the functions are relevant or the given question lacks the parameters required by the function, please output \"<function_call> {\"name\": \"no_function\", \"arguments\": {}}\".\n\nUSER: ' + query}}\n{% if add_generation_prompt %}\n{{ 'ASSISTANT:' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"model_max_length": 8192,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
Reference in New Issue
Block a user