huihui-ai/Huihui-MoE-0.8B-2E
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: huihui-ai/Huihui-MoE-0.8B-2E
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-14 13:37:02 +08:00
commit 21ed8a4974
14 changed files with 152626 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
.gitattributes vendored Normal file
View 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

328
README.md Normal file
View File

@@ -0,0 +1,328 @@
---
license: apache-2.0
base_model:
- Qwen/Qwen3-0.6B
library_name: transformers
license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- moe
---
# huihui-ai/Huihui-MoE-0.8B-2E
## Model Overview
Huihui-MoE-0.8B-2E is a **Mixture of Experts (MoE)** language model developed by **huihui.ai**, built upon the **[Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)** base model. It enhances the standard Transformer architecture by replacing MLP layers with MoE layers, each containing 2 experts, to achieve high performance with efficient inference. The model is designed for natural language processing tasks, including text generation, question answering, and conversational applications.
Huihui-MoE-0.8B-2E is currently the smallest MoE model and can be scaled to include more experts. It has not been fine-tuned and can be fine-tuned according to your specific requirements.
If you do not perform fine-tuning, you can use it in the same way as the original model [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B).
After testing,
with 64 experts based on Qwen3-0.6B, the model is approximately at a 17B parameter level,
with 128 experts based on Qwen3-0.6B, the model is approximately at a 34B parameter level.
- **Architecture**: Qwen3MoeForCausalLM model with 2 experts per layer (num_experts=2), activating 1 expert per token (num_experts_per_tok=1).
- **Total Parameters**: ~0.88 billion (0.8B)
- **Activated Parameters**: ~0.62 billion (0.6B) during inference, comparable to Qwen3-0.6B
- **Developer**: huihui.ai
- **Release Date**: June 2025
- **License**: Inherits the license of the Qwen3 base model (apache-2.0)
## Training
- **Base Model**: Qwen3-0.6B, pre-trained by the Qwen team.
- **Conversion**: The model copies embeddings, self-attention, and normalization weights from Qwen3-0.6B, replacing MLP layers with MoE layers (2 experts). Gating weights are randomly initialized.
- **Fine-Tuning**: Not fine-tuned; users are recommended to fine-tune for specific tasks to optimize expert routing.
## Usage
```
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextStreamer
import torch
import os
import signal
import random
import numpy as np
import time
from collections import Counter
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-0.8B-2E"
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
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
messages = []
nothink = False
same_seed = False
skip_prompt=True
skip_special_tokens=True
do_sample = True
def set_random_seed(seed=None):
"""Set random seed for reproducibility. If seed is None, use int(time.time())."""
if seed is None:
seed = int(time.time()) # Convert float to int
random.seed(seed)
np.random.seed(seed)
torch.manual_seed(seed)
torch.cuda.manual_seed_all(seed) # If using CUDA
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
return seed # Return seed for logging if needed
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
self.init_time = time.time() # Record initialization time
self.end_time = None # To store end time
self.first_token_time = None # To store first token generation time
self.token_count = 0 # To track total tokens
def on_finalized_text(self, text: str, stream_end: bool = False):
if self.first_token_time is None and text.strip(): # Set first token time on first non-empty text
self.first_token_time = time.time()
self.generated_text += text
# Count tokens in the generated text
tokens = self.tokenizer.encode(text, add_special_tokens=False)
self.token_count += len(tokens)
print(text, end="", flush=True)
if stream_end:
self.end_time = time.time() # Record end time when streaming ends
if self.stop_flag:
raise StopIteration
def stop_generation(self):
self.stop_flag = True
self.end_time = time.time() # Record end time when generation is stopped
def get_metrics(self):
"""Returns initialization time, first token time, first token latency, end time, total time, total tokens, and tokens per second."""
if self.end_time is None:
self.end_time = time.time() # Set end time if not already set
total_time = self.end_time - self.init_time # Total time from init to end
tokens_per_second = self.token_count / total_time if total_time > 0 else 0
first_token_latency = (self.first_token_time - self.init_time) if self.first_token_time is not None else None
metrics = {
"init_time": self.init_time,
"first_token_time": self.first_token_time,
"first_token_latency": first_token_latency,
"end_time": self.end_time,
"total_time": total_time, # Total time in seconds
"total_tokens": self.token_count,
"tokens_per_second": tokens_per_second
}
return metrics
def generate_stream(model, tokenizer, messages, nothink, skip_prompt, skip_special_tokens, do_sample, max_new_tokens):
input_ids = tokenizer.apply_chat_template(
messages,
tokenize=True,
enable_thinking = not nothink,
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)
generate_kwargs = {}
if do_sample:
generate_kwargs = {
"do_sample": do_sample,
"max_length": max_new_tokens,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"repetition_penalty": 1.2,
"no_repeat_ngram_size": 2
}
else:
generate_kwargs = {
"do_sample": do_sample,
"max_length": max_new_tokens,
"repetition_penalty": 1.2,
"no_repeat_ngram_size": 2
}
print("Response: ", end="", flush=True)
try:
generated_ids = model.generate(
tokens,
attention_mask=attention_mask,
#use_cache=False,
pad_token_id=tokenizer.pad_token_id,
streamer=streamer,
**generate_kwargs
)
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, streamer.get_metrics()
init_seed = set_random_seed()
# List to store activated expert indices
activated_experts = []
# Define hook function to capture gate_probs output
def hook_fn(module, input, output):
# output is gate_probs, shape: [batch_size, sequence_length, num_experts]
gate_probs = output
# Compute top-1 expert indices (since only one expert is activated)
_, topk_indices = gate_probs.topk(1, dim=-1) # Take top-1
# Flatten and store activated expert indices
activated_experts.extend(topk_indices.squeeze(-1).view(-1).cpu().tolist())
hooks = []
for layer in model.model.layers:
hooks.append(layer.mlp.gate.register_forward_hook(hook_fn))
while True:
if same_seed:
set_random_seed(init_seed)
else:
init_seed = set_random_seed()
print(f"\nnothink: {nothink}")
print(f"skip_prompt: {skip_prompt}")
print(f"skip_special_tokens: {skip_special_tokens}")
print(f"do_sample: {do_sample}")
print(f"same_seed: {same_seed}, {init_seed}\n")
user_input = input("User: ").strip()
if user_input.lower() == "/exit":
print("Exiting chat.")
break
if user_input.lower() == "/clear":
messages = []
print("Chat history cleared. Starting a new conversation.")
continue
if user_input.lower() == "/nothink":
nothink = not nothink
continue
if user_input.lower() == "/skip_prompt":
skip_prompt = not skip_prompt
continue
if user_input.lower() == "/skip_special_tokens":
skip_special_tokens = not skip_special_tokens
continue
if user_input.lower().startswith("/same_seed"):
parts = user_input.split()
if len(parts) == 1: # /same_seed (no number)
same_seed = not same_seed # Toggle switch
elif len(parts) == 2: # /same_seed <number>
try:
init_seed = int(parts[1]) # Extract and convert number to int
same_seed = True
except ValueError:
print("Error: Please provide a valid integer after /same_seed")
continue
if user_input.lower() == "/do_sample":
do_sample = not do_sample
continue
if not user_input:
print("Input cannot be empty. Please enter something.")
continue
messages.append({"role": "user", "content": user_input})
activated_experts = []
response, stop_flag, metrics = generate_stream(model, tokenizer, messages, nothink, skip_prompt, skip_special_tokens, do_sample, 40960)
print("\n\nMetrics:")
for key, value in metrics.items():
print(f" {key}: {value}")
# Count the frequency of each activated expert
expert_counts = Counter(activated_experts)
# Print activation statistics
print("\nActivated Expert Statistics:")
for expert_idx, count in sorted(expert_counts.items()):
print(f"Expert {expert_idx}: {count} times")
print("", flush=True)
if stop_flag:
continue
messages.append({"role": "assistant", "content": response})
# Remove all hooks after inference
for h in hooks: h.remove()
```
## 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 Qwen3-0.6B 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-0.8B-2E (available locally or on Hugging Face)
- **Issues**: Report bugs or request features via the repository or please send an email to support@huihui.ai
## Acknowledgments
- Built upon the Qwen3-0.6B model by the Qwen team.
- Powered by the Hugging Face transformers library.

28
added_tokens.json Normal file
View 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
View 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
View 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": 2,
"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
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

6
generation_config.json Normal file
View 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
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ceba24bcc4886bedf40114eeacf1ad0070d4a316c295f6cfa8cdd6b8bc7f19ae
size 1720746408

426
model_params.txt Normal file
View File

@@ -0,0 +1,426 @@
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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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: 2,048 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.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:860,348,416

31
special_tokens_map.json Normal file
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
size 11422654

239
tokenizer_config.json Normal file
View 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
View File

File diff suppressed because one or more lines are too long