初始化项目，由ModelHub XC社区提供模型
Model: huihui-ai/Huihui-MoE-1B-A0.6B-SFT Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
207
README.md
Normal file
207
README.md
Normal file
@@ -0,0 +1,207 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model:
|
||||
- huihui-ai/Huihui-MoE-1B-A0.6B
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- moe
|
||||
datasets:
|
||||
- nvidia/OpenCodeReasoning
|
||||
- unsloth/OpenMathReasoning-mini
|
||||
- FreedomIntelligence/medical-o1-reasoning-SFT
|
||||
---
|
||||
# huihui-ai/Huihui-MoE-1B-A0.6B-SFT
|
||||
|
||||
## Model Overview
|
||||
Huihui-MoE-1B-A0.6B-SFT is a **Mixture of Experts (MoE)** language model developed by **huihui.ai**, built upon the **[huihui-ai/Huihui-MoE-1B-A0.6B](https://huggingface.co/huihui-ai/Huihui-MoE-1B-A0.6B)** base model.
|
||||
The model is designed for natural language processing tasks, including text generation, question answering, and conversational applications.
|
||||
|
||||
|
||||
- **Architecture**: Qwen3MoeForCausalLM model with 3 experts per layer (num_experts=3), activating 1 expert per token (num_experts_per_tok=1).
|
||||
- **Total Parameters**: ~1.1 billion (1B)
|
||||
- **Activated Parameters**: ~0.62 billion (0.6B) during inference, comparable to huihui-ai/Huihui-MoE-1B-A0.6B
|
||||
- **Developer**: huihui.ai
|
||||
- **Release Date**: June 2025
|
||||
- **License**: Inherits the license of the Qwen3 base model (apache-2.0)
|
||||
|
||||
## Training
|
||||
|
||||
This model is obtained through full-parameter fine-tuning. For each dataset(max_length=1024), only the corresponding experts are fine-tuned.
|
||||
|
||||
- **Coding**: First 20k rows of `nvidia/OpenCodeReasoning` dataset for 1 epoch.
|
||||
- **Math**: Entire `unsloth/OpenMathReasoning-mini` dataset for 1 epoch.
|
||||
- **Medical**:First 20k rows of `FreedomIntelligence/medical-o1-reasoning-SFT` dataset for 1 epoch.
|
||||
|
||||
|
||||
## Usage
|
||||
|
||||
```
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
|
||||
import torch
|
||||
import os
|
||||
import signal
|
||||
|
||||
cpu_count = os.cpu_count()
|
||||
print(f"Number of CPU cores in the system: {cpu_count}")
|
||||
half_cpu_count = cpu_count // 2
|
||||
os.environ["MKL_NUM_THREADS"] = str(half_cpu_count)
|
||||
os.environ["OMP_NUM_THREADS"] = str(half_cpu_count)
|
||||
torch.set_num_threads(half_cpu_count)
|
||||
|
||||
print(f"PyTorch threads: {torch.get_num_threads()}")
|
||||
print(f"MKL threads: {os.getenv('MKL_NUM_THREADS')}")
|
||||
print(f"OMP threads: {os.getenv('OMP_NUM_THREADS')}")
|
||||
|
||||
# Load the model and tokenizer
|
||||
NEW_MODEL_ID = "huihui-ai/Huihui-MoE-1B-A0.6B-SFT"
|
||||
print(f"Load Model {NEW_MODEL_ID} ... ")
|
||||
quant_config_4 = BitsAndBytesConfig(
|
||||
load_in_4bit=True,
|
||||
bnb_4bit_compute_dtype=torch.bfloat16,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
llm_int8_enable_fp32_cpu_offload=True,
|
||||
)
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
NEW_MODEL_ID,
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
#quantization_config=quant_config_4,
|
||||
torch_dtype=torch.bfloat16
|
||||
)
|
||||
tokenizer = AutoTokenizer.from_pretrained(NEW_MODEL_ID, trust_remote_code=True)
|
||||
if tokenizer.pad_token is None:
|
||||
tokenizer.pad_token = tokenizer.eos_token
|
||||
tokenizer.pad_token_id = tokenizer.eos_token_id
|
||||
|
||||
initial_messages = [{"role": "system", "content": "You are a helpful assistant."}]
|
||||
messages = initial_messages.copy()
|
||||
enable_thinking = True
|
||||
skip_prompt=True
|
||||
skip_special_tokens=True
|
||||
|
||||
class CustomTextStreamer(TextStreamer):
|
||||
def __init__(self, tokenizer, skip_prompt=True, skip_special_tokens=True):
|
||||
super().__init__(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
|
||||
self.generated_text = ""
|
||||
self.stop_flag = False
|
||||
|
||||
def on_finalized_text(self, text: str, stream_end: bool = False):
|
||||
self.generated_text += text
|
||||
print(text, end="", flush=True)
|
||||
if self.stop_flag:
|
||||
raise StopIteration
|
||||
|
||||
def stop_generation(self):
|
||||
self.stop_flag = True
|
||||
|
||||
def generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, max_new_tokens):
|
||||
input_ids = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
enable_thinking = enable_thinking,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
)
|
||||
attention_mask = torch.ones_like(input_ids, dtype=torch.long)
|
||||
tokens = input_ids.to(model.device)
|
||||
attention_mask = attention_mask.to(model.device)
|
||||
|
||||
streamer = CustomTextStreamer(tokenizer, skip_prompt=skip_prompt, skip_special_tokens=skip_special_tokens)
|
||||
|
||||
def signal_handler(sig, frame):
|
||||
streamer.stop_generation()
|
||||
print("\n[Generation stopped by user with Ctrl+C]")
|
||||
|
||||
signal.signal(signal.SIGINT, signal_handler)
|
||||
|
||||
print("Response: ", end="", flush=True)
|
||||
try:
|
||||
generated_ids = model.generate(
|
||||
tokens,
|
||||
attention_mask=attention_mask,
|
||||
#use_cache=False,
|
||||
max_new_tokens=max_new_tokens,
|
||||
do_sample=True,
|
||||
pad_token_id=tokenizer.pad_token_id,
|
||||
streamer=streamer
|
||||
)
|
||||
del generated_ids
|
||||
except StopIteration:
|
||||
print("\n[Stopped by user]")
|
||||
|
||||
del input_ids, attention_mask
|
||||
torch.cuda.empty_cache()
|
||||
signal.signal(signal.SIGINT, signal.SIG_DFL)
|
||||
|
||||
return streamer.generated_text, streamer.stop_flag
|
||||
|
||||
while True:
|
||||
user_input = input("User: ").strip()
|
||||
if user_input.lower() == "/exit":
|
||||
print("Exiting chat.")
|
||||
break
|
||||
if user_input.lower() == "/clear":
|
||||
messages = initial_messages.copy()
|
||||
print("Chat history cleared. Starting a new conversation.")
|
||||
continue
|
||||
if user_input.lower() == "/nothink":
|
||||
if enable_thinking:
|
||||
enable_thinking = False
|
||||
print("Thinking = False.")
|
||||
else:
|
||||
enable_thinking = True
|
||||
print("Thinking = True.")
|
||||
continue
|
||||
if user_input.lower() == "/skip_prompt":
|
||||
if skip_prompt:
|
||||
skip_prompt = False
|
||||
print("skip_prompt = False.")
|
||||
else:
|
||||
skip_prompt = True
|
||||
print("skip_prompt = True.")
|
||||
continue
|
||||
if user_input.lower() == "/skip_special_tokens":
|
||||
if skip_special_tokens:
|
||||
skip_special_tokens = False
|
||||
print("skip_special_tokens = False.")
|
||||
else:
|
||||
skip_special_tokens = True
|
||||
print("skip_special_tokens = True.")
|
||||
continue
|
||||
if not user_input:
|
||||
print("Input cannot be empty. Please enter something.")
|
||||
continue
|
||||
messages.append({"role": "user", "content": user_input})
|
||||
response, stop_flag = generate_stream(model, tokenizer, messages, enable_thinking, skip_prompt, skip_special_tokens, 14192)
|
||||
print("", flush=True)
|
||||
if stop_flag:
|
||||
continue
|
||||
messages.append({"role": "assistant", "content": response})
|
||||
|
||||
```
|
||||
|
||||
## Applications
|
||||
|
||||
- **Text Generation: Articles**, dialogues, and creative writing.
|
||||
- **Question Answering**: Information retrieval and query resolution.
|
||||
- **Conversational AI**: Multi-turn dialogues for chatbots.
|
||||
- **Research**: Exploration of MoE architectures and efficient model scaling.
|
||||
|
||||
## Limitations
|
||||
|
||||
- **Fine-Tuning Required**: Randomly initialized gating weights may lead to suboptimal expert utilization without fine-tuning.
|
||||
- **Compatibility**: Developed with transformers 4.52.4; ensure matching versions to avoid loading issues.
|
||||
- **Inference Speed**: While efficient for an MoE model, performance depends on hardware (GPU recommended).
|
||||
|
||||
## Ethical Considerations
|
||||
|
||||
- **Bias**: Inherits potential biases from the huihui-ai/Huihui-MoE-1B-A0.6B base model; users should evaluate outputs for fairness.
|
||||
- **Usage**: Intended for research and responsible applications; avoid generating harmful or misleading content.
|
||||
|
||||
## Contact
|
||||
|
||||
- **Developer**: huihui.ai
|
||||
- **Repository**: huihui-ai/Huihui-MoE-1B-A0.6B-SFT (available locally or on Hugging Face)
|
||||
- **Issues**: Report bugs or request features via the repository or please send an email to support@huihui.ai
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
38
config.json
Normal file
38
config.json
Normal file
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3MoeForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"decoder_sparse_step": 1,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 28,
|
||||
"mlp_only_layers": [],
|
||||
"model_type": "qwen3_moe",
|
||||
"moe_intermediate_size": 3072,
|
||||
"norm_topk_prob": true,
|
||||
"num_attention_heads": 16,
|
||||
"num_experts": 3,
|
||||
"num_experts_per_tok": 1,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"output_router_logits": false,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ef43b78252b8960cc6ba8ee75e7901a6098a702bc9e688d6f12a23432fceb11
|
||||
size 2249296512
|
||||
510
model_params.txt
Normal file
510
model_params.txt
Normal file
@@ -0,0 +1,510 @@
|
||||
Model Parameter Distribution:
|
||||
------------------------------------------------------------
|
||||
model.embed_tokens.weight: 155,582,464 parameters, device cuda:0
|
||||
model.layers.0.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.0.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.0.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.0.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.0.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.0.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.0.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.0.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.0.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.1.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.1.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.1.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.1.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.1.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.1.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.1.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.1.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.1.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.2.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.2.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.2.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.2.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.2.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.2.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.2.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.2.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.2.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.3.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.3.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.3.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.3.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.3.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.3.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.3.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.3.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.3.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.4.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.4.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.4.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.4.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.4.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.4.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.4.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.4.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.4.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.5.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.5.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.5.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.5.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.5.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.5.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.5.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.5.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.5.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.6.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.6.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.6.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.6.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.6.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.6.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.6.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.6.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.6.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.7.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.7.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.7.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.7.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.7.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.7.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.7.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.7.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.7.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.8.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.8.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.8.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.8.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.8.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.8.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.8.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.8.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.8.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.9.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.9.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.9.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.9.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.9.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.9.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.9.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.9.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.9.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.10.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.10.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.10.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.10.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.10.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.10.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.10.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.10.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.10.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.11.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.11.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.11.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.11.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.11.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.11.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.11.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.11.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.11.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.12.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.12.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.12.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.12.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.12.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.12.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.12.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.12.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.12.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.13.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.13.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.13.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.13.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.13.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.13.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.13.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.13.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.13.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.14.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.14.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.14.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.14.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.14.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.14.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.14.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.14.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.14.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.15.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.15.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.15.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.15.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.15.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.15.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.15.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.15.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.15.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.16.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.16.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.16.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.16.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.16.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.16.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.16.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.16.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.16.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.17.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.17.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.17.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.17.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.17.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.17.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.17.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.17.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.17.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.18.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.18.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.18.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.18.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.18.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.18.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.18.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.18.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.18.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.19.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.19.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.19.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.19.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.19.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.19.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.19.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.19.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.19.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.20.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.20.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.20.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.20.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.20.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.20.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.20.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.20.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.20.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.21.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.21.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.21.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.21.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.21.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.21.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.21.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.21.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.21.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.22.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.22.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.22.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.22.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.22.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.22.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.22.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.22.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.22.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.23.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.23.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.23.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.23.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.23.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.23.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.23.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.23.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.23.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.24.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.24.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.24.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.24.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.24.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.24.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.24.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.24.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.24.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.25.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.25.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.25.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.25.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.25.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.25.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.25.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.25.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.25.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.26.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.26.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.26.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.26.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.26.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.26.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.26.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.26.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.26.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.27.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.27.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.27.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
|
||||
model.layers.27.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
|
||||
model.layers.27.self_attn.q_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.27.self_attn.k_norm.weight: 128 parameters, device cuda:0
|
||||
model.layers.27.mlp.gate.weight: 3,072 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
|
||||
model.layers.27.input_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.layers.27.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
|
||||
model.norm.weight: 1,024 parameters, device cuda:0
|
||||
------------------------------------------------------------
|
||||
Total Model Parameter Count:1,124,618,240
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"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:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
|
||||
size 11422934
|
||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user