初始化项目，由ModelHub XC社区提供模型
Model: EphAsad/Atem-4B Source: Original Platform
This commit is contained in:
ModelHub XC
46
.gitattributes
vendored
Normal file
46
.gitattributes
vendored
Normal file
@@ -0,0 +1,46 @@
|
||||
*.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
|
||||
Qwen3-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen3-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen3-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Logo.png filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Atem-4b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Atem-4b.Q4_K_M.gguf
Normal file
3
Atem-4b.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f45a0303c02280405ec07e19a323bb262f286642d6353028eadd91ef04515e7a
|
||||
size 2497281376
|
||||
3
Atem-4b.Q5_K_M.gguf
Normal file
3
Atem-4b.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9cbd9f9f460608b4f973f4934d59584201d563c2f0da10141056374e3d04dac
|
||||
size 2889514336
|
||||
3
Atem-4b.Q8_0.gguf
Normal file
3
Atem-4b.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4daf03735f0db69ed0455e7666b616f290381d55061305d2cb8a90cfb5cd315
|
||||
size 4280405856
|
||||
3
Logo.png
Normal file
3
Logo.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:036d268ac79d1a5355a5ea602fc02ba312f4938c3506ddfa148ec7de44b69607
|
||||
size 981796
|
||||
59
Modelfile
Normal file
59
Modelfile
Normal file
@@ -0,0 +1,59 @@
|
||||
|
||||
FROM Atem-4B.Q8_0.gguf
|
||||
TEMPLATE """{{- if .Messages }}
|
||||
{{- if or .System .Tools }}<|im_start|>system
|
||||
{{- if .System }}
|
||||
{{ .System }}
|
||||
{{- end }}
|
||||
{{- if .Tools }}
|
||||
|
||||
# Tools
|
||||
|
||||
You may call one or more functions to assist with the user query.
|
||||
|
||||
You are provided with function signatures within <tools></tools> XML tags:
|
||||
<tools>
|
||||
{{- range .Tools }}
|
||||
{"type": "function", "function": {{ .Function }}}
|
||||
{{- end }}
|
||||
</tools>
|
||||
|
||||
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||
<tool_call>
|
||||
{"name": <function-name>, "arguments": <args-json-object>}
|
||||
</tool_call>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- range $i, $_ := .Messages }}
|
||||
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
|
||||
{{- if eq .Role "user" }}<|im_start|>user
|
||||
{{ .Content }}<|im_end|>
|
||||
{{ else if eq .Role "assistant" }}<|im_start|>assistant
|
||||
{{ if .Content }}{{ .Content }}
|
||||
{{- else if .ToolCalls }}<tool_call>
|
||||
{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||
{{ end }}</tool_call>
|
||||
{{- end }}{{ if not $last }}<|im_end|>
|
||||
{{ end }}
|
||||
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||
<tool_response>
|
||||
{{ .Content }}
|
||||
</tool_response><|im_end|>
|
||||
{{ end }}
|
||||
{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant
|
||||
{{ end }}
|
||||
{{- end }}
|
||||
{{- else }}
|
||||
{{- if .System }}<|im_start|>system
|
||||
{{ .System }}<|im_end|>
|
||||
{{ end }}{{ if .Prompt }}<|im_start|>user
|
||||
{{ .Prompt }}<|im_end|>
|
||||
{{ end }}<|im_start|>assistant
|
||||
{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}"""
|
||||
PARAMETER stop "<|im_end|>"
|
||||
PARAMETER stop "<|im_start|>"
|
||||
PARAMETER temperature 0.6
|
||||
PARAMETER min_p 0.0
|
||||
PARAMETER top_k 20
|
||||
PARAMETER top_p 0.95
|
||||
PARAMETER repeat_penalty 1
|
||||
368
README.md
Normal file
368
README.md
Normal file
@@ -0,0 +1,368 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-4B
|
||||
tags:
|
||||
- unsloth
|
||||
- lora
|
||||
- qwen3
|
||||
- reasoning
|
||||
- distillation
|
||||
- chain-of-thought
|
||||
datasets:
|
||||
- mitroitskii/OpenR1-Math-220k-formatted
|
||||
- Jackrong/Claude-opus-4.6-TraceInversion-9000x
|
||||
- Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned
|
||||
- WithinUsAI/MiniMax_M2.7_Distilled_5k
|
||||
- FreedomIntelligence/medical-o1-reasoning-SFT
|
||||
- Modotte/CodeX-2M-Thinking
|
||||
- trjxter/DeepSeek-V4-Pro-Reasoning-8000x
|
||||
- nvidia/OpenCodeReasoning
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
|
||||
|
||||
# Atem-4B
|
||||
|
||||
*Ancient logic. Modern intelligence.*
|
||||
|
||||
A 4B reasoning model trained via a single CoT-preserving SFT pass directly on Qwen3-4B, distilling multi-domain reasoning capability from frontier teacher models while keeping the base model's native thinking capability intact.
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Atem-4B is a 4B parameter reasoning model built via a single supervised fine-tuning pass on raw Qwen3-4B. Unlike the earlier 0.6B Atem line, which erased Qwen3's native thinking mode in Stage 1 and re-imposed an externally-distilled reasoning style in Stage 2, Atem-4B is trained in one combined CoT-preserving pass — building reasoning capability on top of the base model's intact native foundation rather than on a cleared one.
|
||||
|
||||
This is currently the **flagship model in the Atem series** and the first to use full 16-bit LoRA (not QLoRA) on a Qwen3 base, enabled by the available VRAM headroom at this scale.
|
||||
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
| Property | Value |
|
||||
| --- | --- |
|
||||
| **Base model** | Qwen/Qwen3-4B |
|
||||
| **Training method** | Single-pass CoT-Preserving LoRA SFT |
|
||||
| **LoRA config** | r=64, alpha=128, dropout=0.05 |
|
||||
| **Target modules** | q, k, v, o, gate, up, down projections |
|
||||
| **Parameters** | ~4.02B |
|
||||
| **Trainable (LoRA) params** | 125,042,688 (3.11% of base) |
|
||||
| **Training records** | 56,573 (after token-length filtering) |
|
||||
| **Think / No-think split** | 85% / 15% |
|
||||
| **Epochs** | 2 (ceiling; early stopping patience=3) |
|
||||
| **Effective batch size** | 64 (batch 8 × grad accum 8) |
|
||||
| **Learning rate** | 1e-4, cosine schedule, 5% warmup |
|
||||
| **Max sequence length** | 6,144 tokens |
|
||||
| **Precision** | bfloat16 (full 16-bit LoRA, not QLoRA) |
|
||||
| **Hardware** | NVIDIA A100-SXM4 80GB |
|
||||
| **License** | Apache 2.0 |
|
||||
|
||||
---
|
||||
|
||||
## Design Notes
|
||||
|
||||
**Why a single combined pass?**
|
||||
The 0.6B Atem pipeline (Stage 1: erase thinking → Stage 2: rebuild with external CoT) created two compounding problems: the erasure pass cost real capability on multi-step reasoning relative to the base model, and the rebuild pass re-imposed an external reasoning style on a foundation that had already been structurally altered. Qualitative benchmarking confirmed this — base Qwen3-0.6B in thinking mode self-corrected on problems the no-think Atem-0.6B got wrong, and lm-eval showed a real ARC-Challenge regression after Stage 2. Atem-4B skips the erasure entirely: one pass, intact native reasoning, externally-distilled CoT styles layered on top of something that still works.
|
||||
|
||||
**Why full 16-bit LoRA?**
|
||||
Every prior Atem script used QLoRA because VRAM was the binding constraint at 0.6B–3B. At 4B with an 80GB A100, full 16-bit LoRA requires ~33GB — comfortably inside budget. Full 16-bit is both marginally faster and marginally more accurate than QLoRA at equivalent effective batch sizes, since QLoRA pays a real compute cost on quantize/dequantize operations at each step.
|
||||
|
||||
**Why r=64?**
|
||||
r=32 represented 3.54% of the 0.6B model but only 0.82% of a 14B model — LoRA params scale roughly linearly with hidden size while total model params scale closer to quadratically. At 4B, r=64 recovers 3.11% proportional capacity, close to the proven 0.6B baseline, without jumping to the "very complex" territory of r=128+.
|
||||
|
||||
---
|
||||
|
||||
## Intended Use
|
||||
|
||||
Atem-4B is designed for general reasoning tasks where structured, step-by-step thinking adds value:
|
||||
|
||||
- Multi-step mathematical reasoning
|
||||
- Code explanation, implementation, and debugging
|
||||
- Analytical reasoning and argument evaluation
|
||||
- Scientific explanation requiring technical depth
|
||||
- Logic, fallacy identification, and conditional reasoning
|
||||
- Concept explanation across diverse domains
|
||||
|
||||
Atem-4B is **not** designed for real-time information retrieval, factual lookup requiring post-training knowledge, or tasks where a fast direct answer without reasoning is preferred — use Atem-0.6B or Atem-Savant-0.6B for those.
|
||||
|
||||
---
|
||||
|
||||
## Training Data
|
||||
|
||||
Atem-4B was trained on a corpus assembled from eight sources covering mathematics, coding, general reasoning, scientific reasoning, and medical reasoning. All sources include explicit chain-of-thought reasoning traces; 85% of training records were formatted with full think traces and 15% as direct answers to maintain no-think capability.
|
||||
|
||||
| Dataset | Records | Source / Teacher |
|
||||
| --- | --- | --- |
|
||||
| mitroitskii/OpenR1-Math-220k-formatted | 10,000 | DeepSeek-R1 — Mathematics (correctness-filtered) |
|
||||
| Jackrong/Claude-opus-4.6-TraceInversion-9000x | 7,000 | Claude Opus 4.6 — Trace Inversion |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (General-Math) | 8,000 | Kimi K2.5 — Mathematical Reasoning |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (General-Distillation) | 8,000 | Kimi K2.5 — General Reasoning |
|
||||
| Jackrong/Kimi-K2.5-Reasoning-1M-Cleaned (PHD-Science) | 8,000 | Kimi K2.5 — Scientific Reasoning |
|
||||
| WithinUsAI/MiniMax_M2.7_Distilled_5k | 5,000 | MiniMax M2.7 |
|
||||
| FreedomIntelligence/medical-o1-reasoning-SFT | 6,000 | Medical reasoning (English config) |
|
||||
| Modotte/CodeX-2M-Thinking | 15,000 | Mixed — Coding with CoT |
|
||||
| trjxter/DeepSeek-V4-Pro-Reasoning-8000x | ~8,000 | DeepSeek-V4-Pro |
|
||||
| nvidia/OpenCodeReasoning | 15,000 | Mixed — Competitive coding |
|
||||
| **Total (post-filter)** | **56,573** | |
|
||||
|
||||
Non-English reasoning traces (primarily CJK) were filtered at the trace level using an ASCII-ratio threshold; records with CJK traces were retained as no-think records rather than discarded entirely. Traces from all sources were passed via the `reasoning_content` message key rather than manual `<think>...</think>` concatenation, preventing silent truncation when reasoning traces contain the literal substring `</think>`.
|
||||
|
||||
---
|
||||
|
||||
## Training Configuration
|
||||
|
||||
```python
|
||||
# Key hyperparameters
|
||||
lora_r = 64
|
||||
lora_alpha = 128
|
||||
lora_dropout = 0.05
|
||||
max_seq_length = 6144
|
||||
learning_rate = 1e-4
|
||||
lr_scheduler = 'cosine'
|
||||
warmup_ratio = 0.05
|
||||
batch_size = 8
|
||||
grad_accumulation = 8 # effective batch size: 64
|
||||
num_epochs = 2 # ceiling — early stopping may cut short
|
||||
eval_steps = 150
|
||||
early_stopping_patience = 3
|
||||
early_stopping_threshold = 0.001
|
||||
nothink_ratio = 0.15
|
||||
load_in_4bit = False # full 16-bit LoRA
|
||||
dtype = bfloat16
|
||||
```
|
||||
|
||||
Training used Unsloth with `train_on_responses_only` masking — loss was computed exclusively on assistant response tokens including reasoning traces for think records. Early stopping halts training automatically when validation loss fails to improve by more than 0.001 across three consecutive evaluation windows, preventing wasted compute at plateau. `load_best_model_at_end=True` ensures the merged checkpoint reflects the best-validation-loss state rather than the final training step.
|
||||
|
||||
Atem's default identity is baked into the chat template via a Jinja else-branch injection: callers without an explicit system message receive the Atem persona by default; explicit system messages override it normally. Verified against the real Qwen3-4B tokenizer before training began.
|
||||
|
||||
---
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Benchmark Results
|
||||
|
||||
Evaluated against base Qwen3-4B (`Qwen/Qwen3-4B`) using lm-evaluation-harness. Both models were loaded in 4-bit for evaluation.
|
||||
|
||||
| Task | Base (Qwen3-4B) | Atem-4B | Delta |
|
||||
| --- | --- | --- | --- |
|
||||
| ARC-Challenge (0-shot, acc_norm) | 53.1% | **54.5%** | +1.5pp ✓ |
|
||||
| GSM8K (5-shot, strict-match) | 82.8% | 80.1% | −2.7pp ⚠ |
|
||||
| HellaSwag (0-shot, acc_norm) | 66.9% | **69.8%** | **+2.9pp** ✓ |
|
||||
| MMLU (0-shot, acc) | 68.4% | 68.7% | +0.3pp — |
|
||||
|
||||
**HellaSwag (+2.9pp, 6.2σ)** is the headline lm-eval result. This benchmark uses normalised log-likelihood scoring over multiple-choice options — it is insensitive to output formatting and cannot be influenced by style changes in generation. A ~3pp improvement here represents real commonsense reasoning transfer from the training corpus.
|
||||
|
||||
**GSM8K note:** The base Qwen3-4B achieves 82.8% on GSM8K — near the ceiling for this model class (comparable to Llama-3.1-8B-Instruct at 78.0%). The −2.7pp regression is likely a formatting artifact: Qwen3-4B in default thinking mode naturally produces `#### {answer}` format that lm-eval's strict-match regex extracts cleanly, while Atem-4B's CoT training may have shifted terminal answer formatting slightly. The math capability itself does not appear regressed — the qualitative benchmark showed correct solutions to the same category of problems, and HellaSwag's +2.9pp gain (format-independent, log-likelihood scoring) is the stronger signal for genuine reasoning improvement.
|
||||
|
||||
**MMLU (+0.3pp)** is within the combined bootstrap standard error of ±0.5pp (0.6σ) and should not be read as a reliable improvement at the aggregate level. The category breakdown tells a more consistent story: Social Sciences (+0.8pp) and Other (+0.7pp) both improved while STEM was flat (−0.3pp), matching the pattern seen across all other benchmarks — reasoning-oriented gains, no curriculum-knowledge gains. This is expected given the training corpus composition.
|
||||
|
||||
| MMLU Category | Base | Atem-4B | Delta |
|
||||
| --- | --- | --- | --- |
|
||||
| STEM | 69.1% | 68.8% | −0.3pp |
|
||||
| Other | 71.3% | **72.2%** | +0.8pp |
|
||||
| Social Sciences | 77.9% | **78.7%** | +0.7pp |
|
||||
| Humanities | 59.7% | 59.7% | +0.1pp |
|
||||
|
||||
|
||||
|
||||
|
||||
### Qualitative Evaluation
|
||||
|
||||
Atem-4B was evaluated against base Qwen3-4B across 30 domain-representative questions spanning coding, mathematics, analytical reasoning, general knowledge, and language. Key findings:
|
||||
|
||||
| Domain | Questions | Outcome |
|
||||
| --- | --- | --- |
|
||||
| Coding | 8 | Atem — more precise, correctly uses `time.perf_counter()`, cleaner implementations |
|
||||
| Mathematics | 6 | Atem — correct on train speed (72 km/h), circular seating (12), Monty Hall (full simulation proof) |
|
||||
| Analytical Reasoning | 6 | Atem — notably stronger on multi-explanation paradoxes and policy consequence chains |
|
||||
| General Knowledge | 5 | Atem — Rayleigh scattering with λ⁻⁴ scaling, Hamiltonian dynamics on perpetual motion |
|
||||
| Language & Logic | 5 | Comparable |
|
||||
|
||||
The CoT-preserving design is visible in the outputs: Atem-4B produces selective think traces — engaging reasoning for complex problems, suppressing it for straightforward ones — rather than the uniform marathon traces (2000+ words) that base Qwen3-4B produces by default. This reflects the 85/15 think/no-think training split working as intended.
|
||||
|
||||
---
|
||||
|
||||
## Usage
|
||||
|
||||
### Transformers
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
import torch
|
||||
|
||||
model_name = "EphAsad/Atem-4B"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Explain the Monty Hall problem and why switching doors gives 2/3 probability."
|
||||
}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to(model.device)
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
input_ids=inputs,
|
||||
max_new_tokens=2000,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
top_k=20,
|
||||
do_sample=True,
|
||||
repetition_penalty=1.1,
|
||||
)
|
||||
|
||||
response = tokenizer.decode(
|
||||
output[0][inputs.shape[1]:],
|
||||
skip_special_tokens=True
|
||||
)
|
||||
print(response)
|
||||
```
|
||||
|
||||
### Unsloth (faster inference)
|
||||
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
import torch
|
||||
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name="EphAsad/Atem-4B",
|
||||
max_seq_length=6144,
|
||||
dtype=torch.bfloat16,
|
||||
load_in_4bit=True,
|
||||
)
|
||||
FastLanguageModel.for_inference(model)
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Given a sorted array with one duplicate, find it in O(log n) time."
|
||||
}
|
||||
]
|
||||
|
||||
inputs = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=True,
|
||||
add_generation_prompt=True,
|
||||
return_tensors="pt"
|
||||
).to("cuda")
|
||||
|
||||
with torch.no_grad():
|
||||
output = model.generate(
|
||||
input_ids=inputs,
|
||||
max_new_tokens=2000,
|
||||
temperature=0.6,
|
||||
top_p=0.95,
|
||||
top_k=20,
|
||||
do_sample=True,
|
||||
)
|
||||
|
||||
print(tokenizer.decode(
|
||||
output[0][inputs.shape[1]:],
|
||||
skip_special_tokens=True
|
||||
))
|
||||
```
|
||||
|
||||
### Ollama
|
||||
|
||||
```bash
|
||||
# Recommended — best speed/quality balance
|
||||
ollama run hf.co/EphAsad/Atem-4B:Q4_K_M
|
||||
|
||||
# Higher quality
|
||||
ollama run hf.co/EphAsad/Atem-4B:Q5_K_M
|
||||
|
||||
# Near-lossless
|
||||
ollama run hf.co/EphAsad/Atem-4B:Q8_0
|
||||
```
|
||||
|
||||
### llama.cpp
|
||||
|
||||
```bash
|
||||
llama-server -hf EphAsad/Atem-4B:Q4_K_M
|
||||
```
|
||||
|
||||
### Sampling Parameters
|
||||
|
||||
Qwen3's own published guidance for thinking mode recommends `temperature=0.6, top_p=0.95, top_k=20`. These are the parameters used in the qualitative benchmark above and are recommended for general use. Do not use greedy decoding (`temperature=0`) with thinking mode — Qwen3's documentation explicitly warns this can cause repetition and degeneration.
|
||||
|
||||
### System Prompt
|
||||
|
||||
Atem-4B's identity is baked into the chat template and activates automatically when no system message is provided. For manual override:
|
||||
|
||||
```
|
||||
You are Atem, a precise and analytical reasoning assistant. You approach
|
||||
every problem methodically — identifying core concepts, reasoning step by
|
||||
step, and arriving at well-supported conclusions. You show your thinking
|
||||
clearly and are thorough, direct, and intellectually honest.
|
||||
```
|
||||
|
||||
### Available Files
|
||||
|
||||
| File | Size | Description |
|
||||
| --- | --- | --- |
|
||||
| `model.safetensors` | ~8 GB | Full bfloat16 merged weights |
|
||||
| `Atem-4b.Q4_K_M.gguf` | ~2.5 GB | 4-bit quantised — recommended |
|
||||
| `Atem-4b.Q5_K_M.gguf` | ~2.89 GB | 5-bit quantised |
|
||||
| `Atem-4b.Q8_0.gguf` | ~4.5 GB | 8-bit quantised — near-lossless |
|
||||
|
||||
---
|
||||
|
||||
## Known Limitations
|
||||
|
||||
**GSM8K formatting sensitivity.** As noted in the evaluation section, the GSM8K regression is likely a formatting artifact rather than a capability regression. For production math applications, verify that your prompting setup elicits answers in the format your extraction logic expects.
|
||||
|
||||
**6,144 token sequence length ceiling.** The training corpus's longest reasoning traces (competitive programming, advanced mathematics) exceed 6,144 tokens and were dropped during formatting. The model has not been exposed to very long chain-of-thought traces and may perform below its potential on problems that genuinely require extended reasoning chains. Raise `max_seq_length` at inference time to allow longer generation budgets.
|
||||
|
||||
**CoT activation is selective.** Atem-4B does not think on every question — the 85/15 training split means it has learned to engage reasoning for complex problems and skip it for simpler ones. If you require thinking traces on a specific query type that the model is treating as simple, an explicit instruction in the system prompt can encourage it.
|
||||
|
||||
**Single-pass SFT, no RLHF or DPO.** Atem-4B has not undergone preference optimisation. Responses are accurate and structured but may not be as reliably aligned with user preferences in open-ended creative or instructional tasks compared to models that have undergone preference training.
|
||||
|
||||
---
|
||||
|
||||
## Roadmap
|
||||
|
||||
- **Atem-14B:** Single CoT-preserving pass on Qwen3-14B with the same methodology, full 16-bit LoRA, r=64
|
||||
|
||||
---
|
||||
|
||||
## Citation
|
||||
|
||||
```bibtex
|
||||
@misc{atem_4b_2026,
|
||||
author = {Asad, Zain},
|
||||
title = {Atem-4B: A 4B CoT-Preserving Reasoning Model via
|
||||
Single-Pass SFT on Qwen3},
|
||||
year = {2026},
|
||||
publisher = {HuggingFace},
|
||||
howpublished = {\url{https://huggingface.co/EphAsad/Atem-4B}},
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), consistent with the base model Qwen/Qwen3-4B.
|
||||
|
||||
---
|
||||
|
||||
Built independently by Zain Asad — [EphAsad](https://huggingface.co/EphAsad)
|
||||
100
chat_template.jinja
Normal file
100
chat_template.jinja
Normal file
@@ -0,0 +1,100 @@
|
||||
{%- 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\n' + 'You are Atem, a precise and analytical reasoning assistant. You approach every problem methodically — identifying core concepts, reasoning step by step, and arriving at well-supported conclusions. You show your thinking clearly and are thorough, direct, and intellectually honest.' + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for forward_message in messages %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- set message = messages[index] %}
|
||||
{%- set current_content = message.content if message.content is not none else '' %}
|
||||
{%- set tool_start = '<tool_response>' %}
|
||||
{%- set tool_start_length = tool_start|length %}
|
||||
{%- set start_of_message = current_content[:tool_start_length] %}
|
||||
{%- set tool_end = '</tool_response>' %}
|
||||
{%- set tool_end_length = tool_end|length %}
|
||||
{%- set start_pos = (current_content|length) - tool_end_length %}
|
||||
{%- if start_pos < 0 %}
|
||||
{%- set start_pos = 0 %}
|
||||
{%- endif %}
|
||||
{%- set end_of_message = current_content[start_pos:] %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
||||
{%- 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>')|last).lstrip('\n') %}
|
||||
{%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
|
||||
{%- set reasoning_content = (reasoning_content.split('<think>')|last).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 %}
|
||||
72
config.json
Normal file
72
config.json
Normal file
@@ -0,0 +1,72 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": null,
|
||||
"torch_dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151669,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.5.5",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"max_length": 40960,
|
||||
"pad_token_id": 151669,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "5.5.0"
|
||||
}
|
||||
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 sha256:8520b0e70fd7af54b49af27c10f06441960ae4a720ca863522511b5cb5885c44
|
||||
size 4967215360
|
||||
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:d2485380e88e4098957cbac158263e7190b9898c13b690b8d7602ef3c2ba9d6d
|
||||
size 3077766632
|
||||
405
model.safetensors.index.json
Normal file
405
model.safetensors.index.json
Normal file
@@ -0,0 +1,405 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 8044936192
|
||||
},
|
||||
"weight_map": {
|
||||
"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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-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-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
|
||||
size 11423114
|
||||
234
tokenizer_config.json
Normal file
234
tokenizer_config.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user