初始化项目，由ModelHub XC社区提供模型
Model: MohitML10/qwen2.5-32b-agentic-orchestrator Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
188
README.md
Normal file
188
README.md
Normal file
@@ -0,0 +1,188 @@
|
||||
---
|
||||
library_name: transformers
|
||||
tags:
|
||||
- agentic
|
||||
- tool-calling
|
||||
- orchestrator
|
||||
- gguf
|
||||
- lora
|
||||
- qwen2
|
||||
- m1300x
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- WaltonFuture/agentic-sft-new
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-32B-Instruct
|
||||
---
|
||||
|
||||
# Qwen2.5-32B Agentic Orchestrator
|
||||
|
||||
**A 32B parameter model fine-tuned for agentic tool-calling workflows — trained on AMD Instinct MI300X (192GB VRAM).**
|
||||
|
||||
Fine-tuned from [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) using LoRA on 22,000 multi-turn agentic conversations covering tool call chaining, structured function calling, and orchestrator decision-making.
|
||||
|
||||
---
|
||||
|
||||
## Why This Model Exists
|
||||
|
||||
Most LLMs are trained to answer questions. This model is trained to **act**.
|
||||
|
||||
The gap this fills: base Qwen2.5-32B-Instruct is a strong reasoner, but it wasn't specifically trained on the behavioral patterns that make agents actually work in production — when to call a tool vs respond directly, how to chain tool calls across multiple turns, how to handle tool failures and escalate correctly, and how to format structured tool calls consistently.
|
||||
|
||||
This fine-tune addresses exactly that. Trained on 22,000 real multi-turn agentic trajectories, the model learns:
|
||||
|
||||
- **Tool call decision-making** — when to act vs when to respond
|
||||
- **Structured tool call formatting** — consistent `<tool_call>` / `<tool_response>` patterns
|
||||
- **Multi-turn chaining** — maintaining context across 9+ turn agentic conversations
|
||||
- **Escalation and handoff patterns** — knowing when to transfer to a human or a different agent
|
||||
- **Constraint awareness** — following system-level policies while serving user goals
|
||||
|
||||
The MI300X was the enabling hardware. Running a 32B model at full BF16 precision with LoRA adapters requires ~80GB+ VRAM minimum. 192GB gave full headroom without quantization tricks during training — meaning the fine-tune captures the full expressiveness of the 32B model.
|
||||
|
||||
---
|
||||
|
||||
## Files in This Repository
|
||||
|
||||
| File | Description |
|
||||
|------|-------------|
|
||||
| `model-q4_k_m.gguf` | **Start here.** Q4_K_M quantized — runs on 24GB RAM, Mac M2 Pro+, single A100 |
|
||||
| `model-00001-of-00002.safetensors` | Full BF16 merged model shard 1 |
|
||||
| `model-00002-of-00002.safetensors` | Full BF16 merged model shard 2 |
|
||||
| `tokenizer.json` | Tokenizer |
|
||||
| `config.json` | Model config |
|
||||
|
||||
---
|
||||
|
||||
## Quickstart
|
||||
|
||||
### Ollama (easiest)
|
||||
```bash
|
||||
ollama run hf.co/MohitML10/qwen2.5-32b-agentic-orchestrator
|
||||
```
|
||||
|
||||
### llama.cpp
|
||||
```bash
|
||||
wget https://huggingface.co/MohitML10/qwen2.5-32b-agentic-orchestrator/resolve/main/model-q4_k_m.gguf
|
||||
|
||||
./llama-cli -m model-q4_k_m.gguf \
|
||||
--chat-template qwen2 \
|
||||
-p "You are an agentic orchestrator. You have access to tools and decide when to use them."
|
||||
```
|
||||
|
||||
### Transformers
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("MohitML10/qwen2.5-32b-agentic-orchestrator")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"MohitML10/qwen2.5-32b-agentic-orchestrator",
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "system",
|
||||
"content": "You are an agentic orchestrator with access to tools. Decide when to call a tool and when to respond directly."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Search for the latest news on LLM benchmarks and summarize the top 3 findings."
|
||||
}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
return_tensors="pt",
|
||||
add_generation_prompt=True
|
||||
).to(model.device)
|
||||
|
||||
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)
|
||||
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
|
||||
```
|
||||
|
||||
### vLLM (for serving)
|
||||
```bash
|
||||
vllm serve MohitML10/qwen2.5-32b-agentic-orchestrator \
|
||||
--dtype bfloat16 \
|
||||
--max-model-len 32768 \
|
||||
--enable-auto-tool-choice \
|
||||
--tool-call-parser hermes
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Training Details
|
||||
|
||||
| Parameter | Value |
|
||||
|-----------|-------|
|
||||
| Base model | Qwen/Qwen2.5-32B-Instruct |
|
||||
| Hardware | AMD Instinct MI300X (192GB VRAM) |
|
||||
| Training method | Supervised Fine-Tuning (SFT) with LoRA |
|
||||
| LoRA rank | 16 |
|
||||
| LoRA alpha | 32 |
|
||||
| LoRA dropout | 0.05 |
|
||||
| Target modules | q_proj, k_proj, v_proj, o_proj |
|
||||
| Trainable parameters | 33.5M / 32.8B (0.10%) |
|
||||
| Dataset | WaltonFuture/agentic-sft-new |
|
||||
| Training samples | 22,000 |
|
||||
| Epochs | 1 |
|
||||
| Batch size | 1 (gradient accumulation 16, effective batch 16) |
|
||||
| Learning rate | 2e-4 |
|
||||
| LR scheduler | Cosine with warmup |
|
||||
| Precision | BF16 |
|
||||
| Max sequence length | 2048 tokens |
|
||||
| Framework | HuggingFace TRL + PEFT |
|
||||
|
||||
---
|
||||
|
||||
## Dataset
|
||||
|
||||
Trained on a filtered subset of [WaltonFuture/agentic-sft-new](https://huggingface.co/datasets/WaltonFuture/agentic-sft-new) — specifically the multi-turn agentic conversation subset (None split label), which contains real customer service and workflow agent trajectories with structured tool calls.
|
||||
|
||||
Conversation format uses `<tool_call>` and `<tool_response>` blocks in standard chat format, directly compatible with Qwen2.5's chat template.
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
|
||||
- **Agentic orchestrators** — the decision layer that decides what tool to call next
|
||||
- **Multi-agent systems** — as the planning layer above specialized worker agents
|
||||
- **Tool-calling pipelines** — structured JSON tool call generation
|
||||
- **AI infrastructure research** — studying agentic behavior at 32B scale
|
||||
|
||||
## Out of Scope
|
||||
|
||||
- General question answering (use base Qwen2.5-32B-Instruct)
|
||||
- Image or multimodal tasks (text only)
|
||||
- Tasks requiring >32k context
|
||||
|
||||
---
|
||||
|
||||
## Hardware Requirements
|
||||
|
||||
| Format | Minimum | Recommended |
|
||||
|--------|---------|-------------|
|
||||
| GGUF Q4_K_M | 24 GB RAM | 32 GB RAM |
|
||||
| BF16 safetensors | 64 GB VRAM | 80 GB VRAM (A100/H100) |
|
||||
|
||||
Runs locally on Mac M2 Pro / M3 Pro or better using the GGUF file.
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
- Trained for 1 epoch on 22k samples — robust on tool-calling patterns but may benefit from further fine-tuning on domain-specific agentic data
|
||||
- No benchmark evaluation yet — before/after comparison on Berkeley Function Calling Leaderboard is a planned next step
|
||||
- Training data is customer service heavy — performance on other agentic domains (code, research, SWE) may vary
|
||||
|
||||
---
|
||||
|
||||
## Developed By
|
||||
|
||||
[MohitML10](https://huggingface.co/MohitML10)
|
||||
|
||||
Trained on AMD Developer Cloud — AMD Instinct MI300X (192GB VRAM) instance.
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
97
config.json
Normal file
97
config.json
Normal file
@@ -0,0 +1,97 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 27648,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 70,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 64,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.9.0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "5.9.0"
|
||||
}
|
||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:151c98a69f21623f05e333f12c92f64d66b3b22e4f5cce0acc52114b899820bf
|
||||
size 49924452408
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3210018d08d9d988a9a8c39e27a9dba458a2abbe5b0082be8b6189d0792bf3b
|
||||
size 15603390216
|
||||
3
model-q4_k_m.gguf
Normal file
3
model-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f72aac32522281c9ba31245b14ed2ead061122d09ed9d041fa26a3ec5a9e00eb
|
||||
size 19851335744
|
||||
779
model.safetensors.index.json
Normal file
779
model.safetensors.index.json
Normal file
@@ -0,0 +1,779 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 32763876352,
|
||||
"total_size": 65527752704
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00002.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.safetensors"
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_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|>"
|
||||
],
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user