初始化项目，由ModelHub XC社区提供模型
Model: serving-d-cause/writing-roleplay-20k-context-nemo-12b-v1.0 Source: Original Platform
This commit is contained in:
ModelHub XC
18
.gitattributes
vendored
Normal file
18
.gitattributes
vendored
Normal file
@@ -0,0 +1,18 @@
|
||||
*.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
|
||||
*.safetensors. filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
155
README.md
Normal file
155
README.md
Normal file
@@ -0,0 +1,155 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
base_model: mistralai/Mistral-Nemo-Base-2407
|
||||
tags:
|
||||
- text-generation
|
||||
- roleplay
|
||||
- storytelling
|
||||
- finetune
|
||||
- qlora
|
||||
- chatml
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
datasets:
|
||||
- openerotica/mixed-rp
|
||||
- anthracite-org/stheno-filtered-v1.1
|
||||
- anthracite-org/kalo_misc_part2
|
||||
- anthracite-org/kalo_opus_misc_240827
|
||||
- anthracite-org/kalo-opus-instruct-22k-no-refusal
|
||||
- Chaser-cz/sonnet35-charcard-roleplay-sharegpt
|
||||
- jondurbin/airoboros-3.2
|
||||
---
|
||||
|
||||
If you like this model, consider joining my discord to provide feedback: https://discord.gg/QXdn8hWSkY
|
||||
|
||||
This is a storywriting and roleplay model with a significant amount of self generated long context multiturn roleplay.
|
||||
|
||||
I downloaded a bit under a thousand cards from chub.ai, and created a synthetic roleplay for each card. I batched as many turns as I could in 4k token chunks in order to maintain coherency over longer context. There was a lot of cleaning and validation between each batch, so a lot of examples were "lost," but the final output seems to be very good quality. The longest conversation is about 20k tokens, and I plan to extend this further as well as broaden the dataset with more examples. The first 4k tokens were generated with Command-R-Plus, with the remainder generated with byroneverson/Mistral-Small-Instruct-2409-abliterated.
|
||||
|
||||
Next, I downloaded the prompt backup from this site, and used them as a seed for some storywriting data:
|
||||
|
||||
https://aetherroom.club/whats-new#backup-update
|
||||
|
||||
I went over it twice with Command-R-Plus. The first time, having it basically write the first draft of the output, the second improving and extending the length of the original output.
|
||||
|
||||
Also included was a subset of the following datasets:
|
||||
|
||||
anthracite-org/stheno-filtered-v1.1
|
||||
|
||||
anthracite-org/kalo_misc_part2
|
||||
|
||||
anthracite-org/kalo_opus_misc_240827
|
||||
|
||||
anthracite-org/kalo-opus-instruct-22k-no-refusal
|
||||
|
||||
Chaser-cz/sonnet35-charcard-roleplay-sharegpt
|
||||
|
||||
(A very small subset) jondurbin/airoboros-3.2
|
||||
|
||||
And some various other data, viewable at openerotica/mixed-rp
|
||||
|
||||
Every line of data was run through a large model in order to filter for low quality, repetition, and underage content.
|
||||
|
||||
There is a LOT more I can do to improve the dataset used to create this model. As of now, the storywriting data is all single shot, where as I'd like to create some examples of "contunue the story in x direction..." and "rewrite it adding/removing these elements". More stable diffusion roleplay prompting data could also be helpful. Roleplay conversations should be exteneded to 32k and beyond.
|
||||
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
||||
|
||||
```yaml
|
||||
base_model: mistralai/Mistral-Nemo-Base-2407
|
||||
model_type: AutoModelForCausalLM
|
||||
tokenizer_type: AutoTokenizer
|
||||
|
||||
load_in_8bit: false
|
||||
load_in_4bit: true
|
||||
strict: false
|
||||
|
||||
datasets:
|
||||
- path: openerotica/mixed-rp
|
||||
type: sharegpt
|
||||
conversation: chatml
|
||||
|
||||
chat_template: chatml
|
||||
adapter: qlora
|
||||
lora_r: 128
|
||||
lora_alpha: 256
|
||||
lora_modules_to_save: [embed_tokens, lm_head]
|
||||
lora_dropout: 0.05
|
||||
lora_target_linear: true
|
||||
lora_target_modules:
|
||||
- gate_proj
|
||||
- down_proj
|
||||
- up_proj
|
||||
- q_proj
|
||||
- v_proj
|
||||
- k_proj
|
||||
- o_proj
|
||||
|
||||
dataset_prepared_path:
|
||||
val_set_size: 0.01
|
||||
output_dir: /workspace/axolotl/mixed-rp-mistral-nemo
|
||||
|
||||
sequence_len: 20000
|
||||
sample_packing: true
|
||||
pad_to_sequence_len: true
|
||||
|
||||
wandb_project: mistral-2
|
||||
wandb_watch:
|
||||
wandb_run_id:
|
||||
wandb_log_model:
|
||||
|
||||
gradient_accumulation_steps: 2
|
||||
micro_batch_size: 1
|
||||
num_epochs: 1
|
||||
optimizer: adamw_torch
|
||||
lr_scheduler: cosine
|
||||
learning_rate: 1e-5
|
||||
train_on_inputs: false
|
||||
group_by_length: false
|
||||
bf16: auto
|
||||
fp16:
|
||||
tf32: false
|
||||
|
||||
gradient_checkpointing: true
|
||||
gradient_checkpointing_kwargs:
|
||||
use_reentrant: false
|
||||
early_stopping_patience:
|
||||
resume_from_checkpoint:
|
||||
logging_steps: 1
|
||||
xformers_attention:
|
||||
flash_attention: true
|
||||
|
||||
warmup_steps: 100
|
||||
evals_per_epoch: 4
|
||||
eval_table_size:
|
||||
saves_per_epoch: 1
|
||||
save_total_limit: 2
|
||||
save_steps:
|
||||
debug:
|
||||
deepspeed:
|
||||
weight_decay: 0.1
|
||||
special_tokens:
|
||||
eos_token: "<|im_end|>"
|
||||
pad_token: "<pad>"
|
||||
bos_token: "<s>"
|
||||
unk_token: "<unk>"
|
||||
tokens:
|
||||
- "<|im_start|>"
|
||||
|
||||
# fsdp:
|
||||
# - full_shard
|
||||
# - auto_wrap
|
||||
# fsdp_config:
|
||||
# fsdp_limit_all_gathers: true
|
||||
# fsdp_sync_module_states: true
|
||||
# fsdp_offload_params: true
|
||||
# fsdp_use_orig_params: false
|
||||
# fsdp_cpu_ram_efficient_loading: true
|
||||
# fsdp_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock
|
||||
# fsdp_state_dict_type: FULL_STATE_DICT
|
||||
# fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
|
||||
# fsdp_sharding_strategy: FULL_SHARD
|
||||
# fsdp_forward_prefetch: false
|
||||
# fsdp_backward_prefetch: BACKWARD_PRE
|
||||
11
chat_template.jinja
Normal file
11
chat_template.jinja
Normal file
@@ -0,0 +1,11 @@
|
||||
{% if not add_generation_prompt is defined %}
|
||||
{% set add_generation_prompt = false %}
|
||||
{% endif %}
|
||||
|
||||
{% for message in messages %}
|
||||
{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}
|
||||
{% endfor %}
|
||||
|
||||
{% if add_generation_prompt %}
|
||||
{{ '<|im_start|>assistant\n' }}
|
||||
{% endif %}
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 131072,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 1024000,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131074
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.45.1"
|
||||
}
|
||||
42
handler.py
Normal file
42
handler.py
Normal file
@@ -0,0 +1,42 @@
|
||||
import os
|
||||
from typing import Any, Dict, List
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, TextGenerationPipeline
|
||||
|
||||
# Ensure your template includes escaped newlines correctly
|
||||
CHAT_TEMPLATE = (
|
||||
"{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}"
|
||||
"{% for message in messages %}"
|
||||
"{{'<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>' + '\\n'}}"
|
||||
"{% endfor %}"
|
||||
"{% if add_generation_prompt %}{{ '<|im_start|>assistant\\n' }}{% endif %}"
|
||||
)
|
||||
|
||||
class EndpointHandler:
|
||||
def __init__(self, model_dir: str, **kwargs: Any):
|
||||
# Load tokenizer and model from provided model_dir
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)
|
||||
# Assign the chat_template under 'default'
|
||||
self.tokenizer.chat_template = {"default": CHAT_TEMPLATE}
|
||||
self.model = AutoModelForCausalLM.from_pretrained(
|
||||
model_dir, trust_remote_code=True, device_map="auto"
|
||||
)
|
||||
self.pipeline = TextGenerationPipeline(
|
||||
model=self.model, tokenizer=self.tokenizer, return_full_text=False
|
||||
)
|
||||
|
||||
def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
|
||||
# Validate input structure
|
||||
messages: List[Dict[str, str]] = data.get("messages")
|
||||
if messages is None:
|
||||
raise ValueError("Request body must include 'messages' array.")
|
||||
|
||||
# Format prompt with proper controlling flag
|
||||
inputs = self.tokenizer.apply_chat_template(
|
||||
messages=messages, add_generation_prompt=True, return_tensors=None
|
||||
)
|
||||
# Generate text
|
||||
gen = self.pipeline(inputs, max_new_tokens=data.get("parameters", {}).get("max_new_tokens", 128))
|
||||
content = gen[0]["generated_text"]
|
||||
|
||||
return {"choices": [{"message": {"role": "assistant", "content": content}}]}
|
||||
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c6b155d89c2985bab2f5f1b0bc9a947a888e74cc9ba495a5a98c14a2c887805
|
||||
size 4865542912
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c2db2877e22bd2a959edfa9b6e6729bc0d48493712c89aaec1de6fde425b945
|
||||
size 4907529344
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fb5ec6238609743188fe466fb927e733efaea1013a4aec066bc09fd97358b2e
|
||||
size 4907529376
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a1f7f3420351abedb797de27d11522402eeede88916a64e81c27b070d47ba3f
|
||||
size 4907529376
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c78a296f505799f31bc962e937b946124befebd2b0cd617b6d04d7ece4a946b
|
||||
size 4907516688
|
||||
370
model.safetensors.index.json
Normal file
370
model.safetensors.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495605760
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00005-of-00005.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
370
pytorch_model.bin.index.json
Normal file
370
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495605760
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.norm.weight": "pytorch_model-00005-of-00005.bin"
|
||||
}
|
||||
}
|
||||
6
requirements.txt
Normal file
6
requirements.txt
Normal file
@@ -0,0 +1,6 @@
|
||||
safetensors
|
||||
torch
|
||||
tqdm
|
||||
numpy
|
||||
jinja2
|
||||
requests
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea88f9940a84ab7e0100bc369506a28ec8d5d821691dc47d4dd63f1bbdf105ed
|
||||
size 17078669
|
||||
8031
tokenizer_config.json
Normal file
8031
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user