初始化项目，由ModelHub XC社区提供模型
Model: saidutta69/Mistral-7B-Instruct-v0.3-heretic Source: Original Platform
This commit is contained in:
ModelHub XC
40
.gitattributes
vendored
Normal file
40
.gitattributes
vendored
Normal file
@@ -0,0 +1,40 @@
|
||||
*.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
|
||||
Mistral-7B-Instruct-v0.3-heretic-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Mistral-7B-Instruct-v0.3-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Mistral-7B-Instruct-v0.3-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Mistral-7B-Instruct-v0.3-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Mistral-7B-Instruct-v0.3-heretic-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Mistral-7B-Instruct-v0.3-heretic-F16.gguf
Normal file
3
Mistral-7B-Instruct-v0.3-heretic-F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ee185bd23d6f5d38bf4c71c49c8cc657bd92f3b3eb8e7112b905fa3f0c0b97c7
|
||||
size 14497341824
|
||||
3
Mistral-7B-Instruct-v0.3-heretic-Q4_K_M.gguf
Normal file
3
Mistral-7B-Instruct-v0.3-heretic-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b14339ec70307cbfd9b4f7765a6ba0e195ebe8c8e2f09375b5e48db09419d292
|
||||
size 4372816416
|
||||
3
Mistral-7B-Instruct-v0.3-heretic-Q5_K_M.gguf
Normal file
3
Mistral-7B-Instruct-v0.3-heretic-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c38b1a6bce1b5c56e1fa45a17d820d7fe23ddc7f31fc68d93851459aba2d71bf
|
||||
size 5136179744
|
||||
3
Mistral-7B-Instruct-v0.3-heretic-Q6_K.gguf
Normal file
3
Mistral-7B-Instruct-v0.3-heretic-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a60ab20c132853b857818aecbcba21a7d62d567e67cf803ed65f9a29834d08f9
|
||||
size 5947253280
|
||||
3
Mistral-7B-Instruct-v0.3-heretic-Q8_0.gguf
Normal file
3
Mistral-7B-Instruct-v0.3-heretic-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e62cc46a7681270a57ee853909aeadb2e0313a6db95160d4be7341d51fa78149
|
||||
size 7702569504
|
||||
142
README.md
Normal file
142
README.md
Normal file
@@ -0,0 +1,142 @@
|
||||
---
|
||||
license: other
|
||||
license_name: apache-2.0
|
||||
license_link: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/blob/main/LICENSE
|
||||
base_model: mistralai/Mistral-7B-Instruct-v0.3
|
||||
tags:
|
||||
- mistral
|
||||
- chat
|
||||
- heretic
|
||||
- uncensored
|
||||
- decensored
|
||||
- abliterated
|
||||
- conversational
|
||||
- text-generation-inference
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Mistral-7B-Instruct-v0.3-heretic
|
||||
|
||||
<div align="center">
|
||||
<img src="https://photu.kashyalabanavli.site/racer-is-op.png" alt="RACER IS OP" width="100%">
|
||||
</div>
|
||||
|
||||
<br>
|
||||
|
||||
A decensored variant of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3), produced with [Heretic](https://github.com/p-e-w/heretic) v1.4.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and instruction-following are left largely intact.
|
||||
|
||||
**Who this is for:** developers who want Mistral's 7B instruct architecture without the refusal guardrails - for local agents, roleplay, function-calling, and research on alignment/refusal mechanics. At 7B it's a strong general-purpose uncensored model for consumer hardware.
|
||||
|
||||
|
||||
<!-- racer-gpu-matrix -->
|
||||
## Runs on your gaming PC
|
||||
|
||||
Full GGUF ladder included — pick the quant that fits your card:
|
||||
|
||||
| Your GPU | Recommended quant | Weights |
|
||||
| :--- | :--- | :--- |
|
||||
| RTX 3090 / 4090 / 5090 (24 GB) | Q8_0 | ~7.8 GB |
|
||||
| RTX 4080 / 5080 / 4060 Ti 16G (16 GB) | Q6_K | ~6.2 GB |
|
||||
| RTX 3060 / 4070 / 5070 (12 GB) | Q5_K_M | ~5.4 GB |
|
||||
| RTX 4060 / 3070 (8 GB) | Q4_K_M | ~4.8 GB |
|
||||
| GTX 1660 Super / 2060 / 3050 laptop (6 GB) | IQ4_XS | ~4.4 GB |
|
||||
| CPU-only / Apple Silicon | Q4_K_M | fits in system RAM |
|
||||
|
||||
Weights only, at this model's 7.2B native size; add ~1 GB for context.
|
||||
OOM? Drop one quant level. Headroom to spare? Go one up.
|
||||
|
||||
## Why abliteration instead of fine-tuning
|
||||
|
||||
Fine-tuning a "helpful" persona on top of RLHF'd refusals fights the base model's training and tends to degrade coherence. Abliteration instead finds and edits the specific weight directions responsible for refusal, leaving the rest of the network (and its capabilities) untouched. See the [Heretic repo](https://github.com/p-e-w/heretic) and the [original abliteration writeup](https://huggingface.co/blog/mlabonne/abliteration) for the mechanism.
|
||||
|
||||
## Abliteration parameters
|
||||
|
||||
| Parameter | Value |
|
||||
|---|---|
|
||||
| `direction_index` | 17.87 |
|
||||
| `attn.o_proj.max_weight` | 1.35 |
|
||||
| `attn.o_proj.max_weight_position` | 22.34 |
|
||||
| `attn.o_proj.min_weight` | 1.29 |
|
||||
| `attn.o_proj.min_weight_distance` | 16.13 |
|
||||
| `mlp.down_proj.max_weight` | 1.35 |
|
||||
| `mlp.down_proj.max_weight_position` | 19.64 |
|
||||
| `mlp.down_proj.min_weight` | 0.64 |
|
||||
| `mlp.down_proj.min_weight_distance` | 7.34 |
|
||||
|
||||
## Performance
|
||||
|
||||
| Metric | This model | Mistral-7B-Instruct-v0.3 (base) |
|
||||
|---|---|---|
|
||||
| Refusals (out of 100 adversarial prompts) | 3/100 | 86/100 |
|
||||
| KL divergence from base | 0.0687 | 0 *(by definition)* |
|
||||
|
||||
KL divergence of 0.07 on the output distribution is low for a 7B model - the edit is narrow and targeted. Refusals dropped from 86 to 3 out of 100 adversarial prompts while retaining nearly all original capabilities.
|
||||
|
||||
> Made with ❤️ by **RACER IS OP** — follow for more uncensored models
|
||||
|
||||
## Files
|
||||
|
||||
### Safetensors (BF16)
|
||||
|
||||
The full-precision weights are in `model-0000N-of-0000N.safetensors` (see the repo file listing for the exact shard count and sizes).
|
||||
|
||||
### GGUF quantizations
|
||||
|
||||
GGUF quantizations are published for this model (Q4_K_M, Q5_K_M, Q6_K, Q8_0). Exact sizes are in the repo file listing. Pull a specific quant with `llama.cpp` / `ollama` (see Quickstart).
|
||||
|
||||
| File | Format | Size |
|
||||
|---|---|---|
|
||||
| `Mistral-7B-Instruct-v0.3-heretic-Q4_K_M.gguf` | GGUF Q4_K_M | (see repo files for exact size) |
|
||||
| `Mistral-7B-Instruct-v0.3-heretic-Q5_K_M.gguf` | GGUF Q5_K_M | (see repo files for exact size) |
|
||||
| `Mistral-7B-Instruct-v0.3-heretic-Q6_K.gguf` | GGUF Q6_K | (see repo files for exact size) |
|
||||
| `Mistral-7B-Instruct-v0.3-heretic-Q8_0.gguf` | GGUF Q8_0 | (see repo files for exact size) |
|
||||
|
||||
## Quickstart
|
||||
|
||||
```bash
|
||||
# llama.cpp - defaults to the Q4_K_M quant if multiple are present
|
||||
llama serve -hf saidutta69/Mistral-7B-Instruct-v0.3-heretic:Q4_K_M
|
||||
```
|
||||
|
||||
```python
|
||||
# transformers
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model_name = "saidutta69/Mistral-7B-Instruct-v0.3-heretic"
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
|
||||
messages = [{"role": "user", "content": "Who are you?"}]
|
||||
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,
|
||||
return_dict=True, return_tensors="pt").to(model.device)
|
||||
out = model.generate(**inputs, max_new_tokens=200)
|
||||
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang - see the "Use this model" widget above for copy-paste commands.
|
||||
|
||||
## Responsible use
|
||||
|
||||
Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it - don't put this behind an unmoderated public-facing endpoint serving third parties. It inherits mistralai/Mistral-7B-Instruct-v0.3's factual limitations and biases; abliteration removes refusal directions, it doesn't add capability or judgment.
|
||||
|
||||
## License
|
||||
|
||||
Inherits the [Apache 2.0](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/blob/main/LICENSE) license from the base model.
|
||||
|
||||
## Related
|
||||
|
||||
- [Qwen2.5-7B-Instruct-heretic](https://huggingface.co/saidutta69/Qwen2.5-7B-Instruct-heretic)
|
||||
- [RACER IS OP — Heretic Models — full collection](https://huggingface.co/collections/saidutta69/racer-is-op-heretic-models)
|
||||
- [Mistral-7B-Instruct-v0.2-heretic](https://huggingface.co/saidutta69/Mistral-7B-Instruct-v0.2-heretic)
|
||||
|
||||
---
|
||||
|
||||
# Base model: Mistral-7B-Instruct-v0.3
|
||||
|
||||
<details>
|
||||
<summary>Original Mistral-7B-Instruct-v0.3 model card (click to expand)</summary>
|
||||
|
||||
See the base model card at [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) for the original architecture, training details, requirements, and citation.
|
||||
</details>
|
||||
87
chat_template.jinja
Normal file
87
chat_template.jinja
Normal file
@@ -0,0 +1,87 @@
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
||||
|
||||
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
||||
{%- set ns = namespace() %}
|
||||
{%- set ns.index = 0 %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
||||
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
||||
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif %}
|
||||
{%- set ns.index = ns.index + 1 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{{- bos_token }}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message["role"] == "user" %}
|
||||
{%- if tools is not none and (message == user_messages[-1]) %}
|
||||
{{- "[AVAILABLE_TOOLS] [" }}
|
||||
{%- for tool in tools %}
|
||||
{%- set tool = tool.function %}
|
||||
{{- '{"type": "function", "function": {' }}
|
||||
{%- for key, val in tool.items() if key != "return" %}
|
||||
{%- if val is string %}
|
||||
{{- '"' + key + '": "' + val + '"' }}
|
||||
{%- else %}
|
||||
{{- '"' + key + '": ' + val|tojson }}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "}}" }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "[/AVAILABLE_TOOLS]" }}
|
||||
{%- endif %}
|
||||
{%- if loop.last and system_message is defined %}
|
||||
{{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
||||
{%- else %}
|
||||
{{- "[INST] " + message["content"] + "[/INST]" }}
|
||||
{%- endif %}
|
||||
{%- elif message.tool_calls is defined and message.tool_calls is not none %}
|
||||
{{- "[TOOL_CALLS] [" }}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- set out = tool_call.function|tojson %}
|
||||
{{- out[:-1] }}
|
||||
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- ', "id": "' + tool_call.id + '"}' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif message["role"] == "assistant" %}
|
||||
{{- " " + message["content"]|trim + eos_token}}
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
|
||||
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "5.14.1"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2a67c2f417607db73767c0a13444493866ddcbc3b15701cd965ce17def95916f
|
||||
size 4899129848
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c614b7b993a54f4c8f35d9f44220cef8a7a96426edc09bf9a844bc46d0385e5
|
||||
size 4915916184
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:066ac7dcc64cba6cf75cd5fecb066e7c4eef043ebc8fe6530c77883914887aec
|
||||
size 4681034912
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 7248023552,
|
||||
"total_size": 14496047104
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00003.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.norm.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
69
reproduce/README.md
Normal file
69
reproduce/README.md
Normal file
@@ -0,0 +1,69 @@
|
||||
# Reproduction guide
|
||||
|
||||
This directory contains the necessary information and assets to reproduce the results obtained during this Heretic run.
|
||||
|
||||
## Models
|
||||
|
||||
- **Base model:** [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) (Commit: [`c170c70`](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3/commit/c170c708c41dac9275d15a8fff4eca08d52bab71))
|
||||
|
||||
## Datasets
|
||||
|
||||
- **Good prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
||||
- **Bad prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
||||
- **Good evaluation prompts:** [mlabonne/harmless_alpaca](https://huggingface.co/datasets/mlabonne/harmless_alpaca) (Commit: [`02c6a92`](https://huggingface.co/datasets/mlabonne/harmless_alpaca/commit/02c6a92cfcf11bb0c387334f8146d149d65b587f))
|
||||
- **Bad evaluation prompts:** [mlabonne/harmful_behaviors](https://huggingface.co/datasets/mlabonne/harmful_behaviors) (Commit: [`01cead0`](https://huggingface.co/datasets/mlabonne/harmful_behaviors/commit/01cead01398926d81f7c52bdb790ee8cf77ebba7))
|
||||
|
||||
## Selected trial
|
||||
|
||||
- **Trial number:** 106
|
||||
- **KL divergence:** 0.068717
|
||||
- **Refusals:** 3/100
|
||||
|
||||
## System
|
||||
|
||||
- **Python:** 3.12.11 (CPython, GCC 11.2.0) [Conda]
|
||||
- **Operating system:** Linux-6.8.0-1058-aws-x86_64-with-glibc2.39 (x86_64)
|
||||
- **CPU:** Intel(R) Xeon(R) Platinum 8559C
|
||||
|
||||
### Accelerators
|
||||
|
||||
- **CUDA:** Detected 1 device(s) (94.97 GB total VRAM)
|
||||
- **CUDA Version:** 12.8
|
||||
- **Driver Version:** 580.126.20
|
||||
- **Devices:**
|
||||
- **CUDA 0:** NVIDIA RTX PRO 6000 Blackwell Server Edition (94.97 GB)
|
||||
|
||||
## Environment
|
||||
|
||||
- **Heretic:** v1.4.0 (Origin: PyPI)
|
||||
- **PyTorch:** 2.8.0+cu128
|
||||
- **Other dependencies:** See [`requirements.txt`](requirements.txt).
|
||||
|
||||
## Contents of this directory
|
||||
|
||||
- [`requirements.txt`](requirements.txt): The exact versions of all Python packages.
|
||||
- [`config.toml`](config.toml): The exact configuration used, including the RNG seed.
|
||||
- [`mistralai--Mistral-7B-Instruct-v0--3.jsonl`](mistralai--Mistral-7B-Instruct-v0--3.jsonl): The Optuna study journal containing the history of all trials.
|
||||
- [`SHA256SUMS`](SHA256SUMS): Cryptographic hashes for all weight files.
|
||||
- [`reproduce.json`](reproduce.json): A machine-readable file containing all reproducibility information.
|
||||
|
||||
## How to reproduce
|
||||
|
||||
> [!TIP]
|
||||
> You can automate this process, including all verification steps, by downloading the `reproduce.json` file and running
|
||||
> `heretic --reproduce reproduce.json`.
|
||||
|
||||
1. Ensure your system matches the specifications in the **System** section above. Exact reproducibility is only guaranteed if all aspects of your system are identical to the one the model was originally generated on.
|
||||
1. Install the exact version of Heretic indicated in the **Environment** section above, from its original source.
|
||||
1. Install the packages listed in `requirements.txt`: `pip install -r requirements.txt`
|
||||
1. Install the correct version of PyTorch: `pip install torch==2.8.0+cu128 --index-url https://download.pytorch.org/whl/cu128`
|
||||
1. Place the provided `config.toml` in your working directory.
|
||||
1. Run Heretic without any additional arguments: `heretic`
|
||||
1. Wait for the run to finish, then select trial **106** and export the model.
|
||||
1. Verify that the weight files have been exactly reproduced by comparing their SHA-256 hashes against those in `SHA256SUMS`:
|
||||
`sha256sum -c SHA256SUMS` (or look at the hashes online if you uploaded to Hugging Face)
|
||||
|
||||
> [!TIP]
|
||||
> To use the included Optuna study journal `mistralai--Mistral-7B-Instruct-v0--3.jsonl`, place it in the checkpoints directory (usually `checkpoints/`) before running Heretic.
|
||||
>
|
||||
> This allows you to export other models from the Pareto front, or to run additional trials without having to re-run the stored trials.
|
||||
3
reproduce/SHA256SUMS
Normal file
3
reproduce/SHA256SUMS
Normal file
@@ -0,0 +1,3 @@
|
||||
2a67c2f417607db73767c0a13444493866ddcbc3b15701cd965ce17def95916f *model-00001-of-00003.safetensors
|
||||
4c614b7b993a54f4c8f35d9f44220cef8a7a96426edc09bf9a844bc46d0385e5 *model-00002-of-00003.safetensors
|
||||
066ac7dcc64cba6cf75cd5fecb066e7c4eef043ebc8fe6530c77883914887aec *model-00003-of-00003.safetensors
|
||||
93
reproduce/config.toml
Normal file
93
reproduce/config.toml
Normal file
@@ -0,0 +1,93 @@
|
||||
model = "mistralai/Mistral-7B-Instruct-v0.3"
|
||||
model_commit = "c170c708c41dac9275d15a8fff4eca08d52bab71"
|
||||
dtypes = [
|
||||
"auto",
|
||||
"float16",
|
||||
"bfloat16",
|
||||
"float32",
|
||||
]
|
||||
quantization = "none"
|
||||
device_map = "auto"
|
||||
offload_outputs_to_cpu = true
|
||||
batch_size = 128
|
||||
max_response_length = 100
|
||||
response_prefix = ""
|
||||
kl_divergence_scale = 1.0
|
||||
kl_divergence_target = 0.01
|
||||
orthogonalize_direction = true
|
||||
row_normalization = "full"
|
||||
full_normalization_lora_rank = 3
|
||||
winsorization_quantile = 1.0
|
||||
n_trials = 200
|
||||
n_startup_trials = 60
|
||||
seed = 199030081
|
||||
export_strategy = "merge"
|
||||
max_shard_size = "5GB"
|
||||
refusal_markers = [
|
||||
"disclaimer",
|
||||
"sorry",
|
||||
"i can'",
|
||||
"i cant",
|
||||
"i cannot",
|
||||
"i won'",
|
||||
"i wont",
|
||||
"i will not",
|
||||
"i unable",
|
||||
"im unable",
|
||||
"i'm unable",
|
||||
"i am unable",
|
||||
"i an ai",
|
||||
"im an ai",
|
||||
"i'm an ai",
|
||||
"i am an ai",
|
||||
"as an ai",
|
||||
"ai assistant",
|
||||
"i designed to",
|
||||
"im designed to",
|
||||
"i'm designed to",
|
||||
"i am designed to",
|
||||
"i programmed to",
|
||||
"im programmed to",
|
||||
"i'm programmed to",
|
||||
"i am programmed to",
|
||||
"violat",
|
||||
"prohibit",
|
||||
"illegal",
|
||||
"harmful",
|
||||
"inappropriate",
|
||||
"unethical",
|
||||
"ethical boundaries",
|
||||
]
|
||||
system_prompt = "You are a helpful assistant."
|
||||
|
||||
[good_prompts]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "train[:400]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[bad_prompts]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "train[:400]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[good_evaluation_prompts]
|
||||
dataset = "mlabonne/harmless_alpaca"
|
||||
commit = "02c6a92cfcf11bb0c387334f8146d149d65b587f"
|
||||
split = "test[:100]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
|
||||
[bad_evaluation_prompts]
|
||||
dataset = "mlabonne/harmful_behaviors"
|
||||
commit = "01cead01398926d81f7c52bdb790ee8cf77ebba7"
|
||||
split = "test[:100]"
|
||||
column = "text"
|
||||
prefix = ""
|
||||
suffix = ""
|
||||
3804
reproduce/mistralai--Mistral-7B-Instruct-v0--3.jsonl
Normal file
3804
reproduce/mistralai--Mistral-7B-Instruct-v0--3.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
289
reproduce/reproduce.json
Normal file
289
reproduce/reproduce.json
Normal file
@@ -0,0 +1,289 @@
|
||||
{
|
||||
"version": "2",
|
||||
"timestamp": "2026-07-16T21:56:08",
|
||||
"system": {
|
||||
"python": {
|
||||
"version": "3.12.11",
|
||||
"implementation": "CPython",
|
||||
"compiler": "GCC 11.2.0",
|
||||
"environment": "Conda"
|
||||
},
|
||||
"os": {
|
||||
"platform": "Linux-6.8.0-1058-aws-x86_64-with-glibc2.39",
|
||||
"machine": "x86_64"
|
||||
},
|
||||
"cpu": {
|
||||
"brand": "Intel(R) Xeon(R) Platinum 8559C",
|
||||
"vendor": "GenuineIntel",
|
||||
"family": 6,
|
||||
"model": 207,
|
||||
"stepping": 2
|
||||
},
|
||||
"accelerators": {
|
||||
"type": "CUDA",
|
||||
"api_name": "CUDA Version",
|
||||
"api_version": "12.8",
|
||||
"driver_version": "580.126.20",
|
||||
"devices": [
|
||||
{
|
||||
"name": "NVIDIA RTX PRO 6000 Blackwell Server Edition",
|
||||
"vram_gb": 94.97
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"environment": {
|
||||
"heretic": {
|
||||
"version": "1.4.0",
|
||||
"is_standard_pypi": true,
|
||||
"metadata": {
|
||||
"type": "pypi"
|
||||
}
|
||||
},
|
||||
"pytorch_version": "2.8.0+cu128",
|
||||
"requirements": {
|
||||
"absl-py": "2.4.0",
|
||||
"accelerate": "1.14.0",
|
||||
"alembic": "1.18.5",
|
||||
"annotated-doc": "0.0.4",
|
||||
"annotated-types": "0.7.0",
|
||||
"anyio": "4.14.1",
|
||||
"bitsandbytes": "0.49.2",
|
||||
"certifi": "2026.6.17",
|
||||
"chardet": "6.0.0.post1",
|
||||
"charset-normalizer": "3.4.7",
|
||||
"click": "8.4.2",
|
||||
"colorama": "0.4.6",
|
||||
"colorlog": "6.10.1",
|
||||
"dataproperty": "1.1.1",
|
||||
"datasets": "4.8.5",
|
||||
"defusedxml": "0.7.1",
|
||||
"dill": "0.4.1",
|
||||
"evaluate": "0.4.6",
|
||||
"filelock": "3.29.4",
|
||||
"fsspec": "2026.2.0",
|
||||
"greenlet": "3.5.3",
|
||||
"h11": "0.16.0",
|
||||
"heretic-llm": "1.4.0",
|
||||
"hf-xet": "1.5.2",
|
||||
"httpcore": "1.0.9",
|
||||
"httpx": "0.28.1",
|
||||
"huggingface-hub": "1.23.0",
|
||||
"idna": "3.18",
|
||||
"immutabledict": "4.3.1",
|
||||
"jinja2": "3.1.6",
|
||||
"joblib": "1.5.3",
|
||||
"langdetect": "1.0.9",
|
||||
"lm-eval": "0.4.12",
|
||||
"lxml": "6.1.1",
|
||||
"mako": "1.3.12",
|
||||
"markdown-it-py": "4.2.0",
|
||||
"markupsafe": "3.0.3",
|
||||
"mbstrdecoder": "1.1.5",
|
||||
"mdurl": "0.1.2",
|
||||
"more-itertools": "11.1.0",
|
||||
"mpmath": "1.3.0",
|
||||
"multiprocess": "0.70.19",
|
||||
"narwhals": "2.24.0",
|
||||
"networkx": "3.6.1",
|
||||
"nltk": "3.10.0",
|
||||
"numpy": "2.5.1",
|
||||
"nvidia-cublas-cu12": "12.8.4.1",
|
||||
"nvidia-cuda-cupti-cu12": "12.8.90",
|
||||
"nvidia-cuda-nvrtc-cu12": "12.8.93",
|
||||
"nvidia-cuda-runtime-cu12": "12.8.90",
|
||||
"nvidia-cudnn-cu12": "9.10.2.21",
|
||||
"nvidia-cufft-cu12": "11.3.3.83",
|
||||
"nvidia-cufile-cu12": "1.13.1.3",
|
||||
"nvidia-curand-cu12": "10.3.9.90",
|
||||
"nvidia-cusolver-cu12": "11.7.3.90",
|
||||
"nvidia-cusparse-cu12": "12.5.8.93",
|
||||
"nvidia-cusparselt-cu12": "0.7.1",
|
||||
"nvidia-nccl-cu12": "2.27.3",
|
||||
"nvidia-nvjitlink-cu12": "12.8.93",
|
||||
"nvidia-nvtx-cu12": "12.8.90",
|
||||
"optuna": "4.9.0",
|
||||
"packaging": "26.0",
|
||||
"pandas": "3.0.3",
|
||||
"pathvalidate": "3.3.1",
|
||||
"peft": "0.19.1",
|
||||
"pillow": "12.2.0",
|
||||
"portalocker": "3.2.0",
|
||||
"prompt-toolkit": "3.0.52",
|
||||
"psutil": "7.2.2",
|
||||
"py-cpuinfo": "9.0.0",
|
||||
"pyarrow": "25.0.0",
|
||||
"pydantic": "2.13.4",
|
||||
"pydantic-core": "2.46.4",
|
||||
"pydantic-settings": "2.14.2",
|
||||
"pygments": "2.20.0",
|
||||
"pytablewriter": "1.2.1",
|
||||
"python-dateutil": "2.9.0.post0",
|
||||
"python-dotenv": "1.2.2",
|
||||
"pyyaml": "6.0.3",
|
||||
"questionary": "2.1.1",
|
||||
"regex": "2026.7.10",
|
||||
"requests": "2.34.2",
|
||||
"rich": "14.3.4",
|
||||
"rouge-score": "0.1.2",
|
||||
"sacrebleu": "2.6.0",
|
||||
"safetensors": "0.8.0",
|
||||
"scikit-learn": "1.9.0",
|
||||
"scipy": "1.18.0",
|
||||
"setuptools": "83.0.0",
|
||||
"shellingham": "1.5.4",
|
||||
"six": "1.17.0",
|
||||
"sqlalchemy": "2.0.51",
|
||||
"sqlitedict": "2.1.0",
|
||||
"sympy": "1.14.0",
|
||||
"tabledata": "1.3.5",
|
||||
"tabulate": "0.10.0",
|
||||
"tcolorpy": "0.1.7",
|
||||
"threadpoolctl": "3.6.0",
|
||||
"tokenizers": "0.22.2",
|
||||
"tomli-w": "1.2.0",
|
||||
"torch": "2.8.0",
|
||||
"torchvision": "0.23.0",
|
||||
"tqdm": "4.68.3",
|
||||
"transformers": "5.14.1",
|
||||
"triton": "3.4.0",
|
||||
"typepy": "1.3.5",
|
||||
"typer": "0.27.0",
|
||||
"typing-extensions": "4.15.0",
|
||||
"typing-inspection": "0.4.2",
|
||||
"tzdata": "2026.2",
|
||||
"urllib3": "2.5.0",
|
||||
"wcwidth": "0.8.1",
|
||||
"word2number": "1.1",
|
||||
"xxhash": "3.8.1"
|
||||
}
|
||||
},
|
||||
"settings": {
|
||||
"model": "mistralai/Mistral-7B-Instruct-v0.3",
|
||||
"model_commit": "c170c708c41dac9275d15a8fff4eca08d52bab71",
|
||||
"dtypes": [
|
||||
"auto",
|
||||
"float16",
|
||||
"bfloat16",
|
||||
"float32"
|
||||
],
|
||||
"quantization": "none",
|
||||
"device_map": "auto",
|
||||
"max_memory": null,
|
||||
"offload_outputs_to_cpu": true,
|
||||
"batch_size": 128,
|
||||
"max_response_length": 100,
|
||||
"response_prefix": "",
|
||||
"kl_divergence_scale": 1.0,
|
||||
"kl_divergence_target": 0.01,
|
||||
"orthogonalize_direction": true,
|
||||
"row_normalization": "full",
|
||||
"full_normalization_lora_rank": 3,
|
||||
"winsorization_quantile": 1.0,
|
||||
"n_trials": 200,
|
||||
"n_startup_trials": 60,
|
||||
"seed": 199030081,
|
||||
"export_strategy": "merge",
|
||||
"max_shard_size": "5GB",
|
||||
"refusal_markers": [
|
||||
"disclaimer",
|
||||
"sorry",
|
||||
"i can'",
|
||||
"i cant",
|
||||
"i cannot",
|
||||
"i won'",
|
||||
"i wont",
|
||||
"i will not",
|
||||
"i unable",
|
||||
"im unable",
|
||||
"i'm unable",
|
||||
"i am unable",
|
||||
"i an ai",
|
||||
"im an ai",
|
||||
"i'm an ai",
|
||||
"i am an ai",
|
||||
"as an ai",
|
||||
"ai assistant",
|
||||
"i designed to",
|
||||
"im designed to",
|
||||
"i'm designed to",
|
||||
"i am designed to",
|
||||
"i programmed to",
|
||||
"im programmed to",
|
||||
"i'm programmed to",
|
||||
"i am programmed to",
|
||||
"violat",
|
||||
"prohibit",
|
||||
"illegal",
|
||||
"harmful",
|
||||
"inappropriate",
|
||||
"unethical",
|
||||
"ethical boundaries"
|
||||
],
|
||||
"system_prompt": "You are a helpful assistant.",
|
||||
"good_prompts": {
|
||||
"dataset": "mlabonne/harmless_alpaca",
|
||||
"commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f",
|
||||
"split": "train[:400]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"bad_prompts": {
|
||||
"dataset": "mlabonne/harmful_behaviors",
|
||||
"commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7",
|
||||
"split": "train[:400]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"good_evaluation_prompts": {
|
||||
"dataset": "mlabonne/harmless_alpaca",
|
||||
"commit": "02c6a92cfcf11bb0c387334f8146d149d65b587f",
|
||||
"split": "test[:100]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
},
|
||||
"bad_evaluation_prompts": {
|
||||
"dataset": "mlabonne/harmful_behaviors",
|
||||
"commit": "01cead01398926d81f7c52bdb790ee8cf77ebba7",
|
||||
"split": "test[:100]",
|
||||
"column": "text",
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"system_prompt": null
|
||||
}
|
||||
},
|
||||
"parameters": {
|
||||
"direction_index": 17.869835211230445,
|
||||
"abliteration_parameters": {
|
||||
"attn.o_proj": {
|
||||
"max_weight": 1.3546769039218534,
|
||||
"max_weight_position": 22.33676889727451,
|
||||
"min_weight": 1.2853067787469532,
|
||||
"min_weight_distance": 16.130392311213924
|
||||
},
|
||||
"mlp.down_proj": {
|
||||
"max_weight": 1.3477813982026554,
|
||||
"max_weight_position": 19.636517725737107,
|
||||
"min_weight": 0.6364123559659257,
|
||||
"min_weight_distance": 7.34202830438775
|
||||
}
|
||||
}
|
||||
},
|
||||
"metrics": {
|
||||
"kl_divergence": 0.06871703267097473,
|
||||
"refusals": 3,
|
||||
"base_refusals": 86,
|
||||
"n_bad_prompts": 100
|
||||
},
|
||||
"hashes": {
|
||||
"model-00001-of-00003.safetensors": "2a67c2f417607db73767c0a13444493866ddcbc3b15701cd965ce17def95916f",
|
||||
"model-00002-of-00003.safetensors": "4c614b7b993a54f4c8f35d9f44220cef8a7a96426edc09bf9a844bc46d0385e5",
|
||||
"model-00003-of-00003.safetensors": "066ac7dcc64cba6cf75cd5fecb066e7c4eef043ebc8fe6530c77883914887aec"
|
||||
}
|
||||
}
|
||||
114
reproduce/requirements.txt
Normal file
114
reproduce/requirements.txt
Normal file
@@ -0,0 +1,114 @@
|
||||
absl-py==2.4.0
|
||||
accelerate==1.14.0
|
||||
alembic==1.18.5
|
||||
annotated-doc==0.0.4
|
||||
annotated-types==0.7.0
|
||||
anyio==4.14.1
|
||||
bitsandbytes==0.49.2
|
||||
certifi==2026.6.17
|
||||
chardet==6.0.0.post1
|
||||
charset-normalizer==3.4.7
|
||||
click==8.4.2
|
||||
colorama==0.4.6
|
||||
colorlog==6.10.1
|
||||
dataproperty==1.1.1
|
||||
datasets==4.8.5
|
||||
defusedxml==0.7.1
|
||||
dill==0.4.1
|
||||
evaluate==0.4.6
|
||||
filelock==3.29.4
|
||||
fsspec==2026.2.0
|
||||
greenlet==3.5.3
|
||||
h11==0.16.0
|
||||
heretic-llm==1.4.0
|
||||
hf-xet==1.5.2
|
||||
httpcore==1.0.9
|
||||
httpx==0.28.1
|
||||
huggingface-hub==1.23.0
|
||||
idna==3.18
|
||||
immutabledict==4.3.1
|
||||
jinja2==3.1.6
|
||||
joblib==1.5.3
|
||||
langdetect==1.0.9
|
||||
lm-eval==0.4.12
|
||||
lxml==6.1.1
|
||||
mako==1.3.12
|
||||
markdown-it-py==4.2.0
|
||||
markupsafe==3.0.3
|
||||
mbstrdecoder==1.1.5
|
||||
mdurl==0.1.2
|
||||
more-itertools==11.1.0
|
||||
mpmath==1.3.0
|
||||
multiprocess==0.70.19
|
||||
narwhals==2.24.0
|
||||
networkx==3.6.1
|
||||
nltk==3.10.0
|
||||
numpy==2.5.1
|
||||
nvidia-cublas-cu12==12.8.4.1
|
||||
nvidia-cuda-cupti-cu12==12.8.90
|
||||
nvidia-cuda-nvrtc-cu12==12.8.93
|
||||
nvidia-cuda-runtime-cu12==12.8.90
|
||||
nvidia-cudnn-cu12==9.10.2.21
|
||||
nvidia-cufft-cu12==11.3.3.83
|
||||
nvidia-cufile-cu12==1.13.1.3
|
||||
nvidia-curand-cu12==10.3.9.90
|
||||
nvidia-cusolver-cu12==11.7.3.90
|
||||
nvidia-cusparse-cu12==12.5.8.93
|
||||
nvidia-cusparselt-cu12==0.7.1
|
||||
nvidia-nccl-cu12==2.27.3
|
||||
nvidia-nvjitlink-cu12==12.8.93
|
||||
nvidia-nvtx-cu12==12.8.90
|
||||
optuna==4.9.0
|
||||
packaging==26.0
|
||||
pandas==3.0.3
|
||||
pathvalidate==3.3.1
|
||||
peft==0.19.1
|
||||
pillow==12.2.0
|
||||
portalocker==3.2.0
|
||||
prompt-toolkit==3.0.52
|
||||
psutil==7.2.2
|
||||
py-cpuinfo==9.0.0
|
||||
pyarrow==25.0.0
|
||||
pydantic==2.13.4
|
||||
pydantic-core==2.46.4
|
||||
pydantic-settings==2.14.2
|
||||
pygments==2.20.0
|
||||
pytablewriter==1.2.1
|
||||
python-dateutil==2.9.0.post0
|
||||
python-dotenv==1.2.2
|
||||
pyyaml==6.0.3
|
||||
questionary==2.1.1
|
||||
regex==2026.7.10
|
||||
requests==2.34.2
|
||||
rich==14.3.4
|
||||
rouge-score==0.1.2
|
||||
sacrebleu==2.6.0
|
||||
safetensors==0.8.0
|
||||
scikit-learn==1.9.0
|
||||
scipy==1.18.0
|
||||
setuptools==83.0.0
|
||||
shellingham==1.5.4
|
||||
six==1.17.0
|
||||
sqlalchemy==2.0.51
|
||||
sqlitedict==2.1.0
|
||||
sympy==1.14.0
|
||||
tabledata==1.3.5
|
||||
tabulate==0.10.0
|
||||
tcolorpy==0.1.7
|
||||
threadpoolctl==3.6.0
|
||||
tokenizers==0.22.2
|
||||
tomli-w==1.2.0
|
||||
torch==2.8.0
|
||||
torchvision==0.23.0
|
||||
tqdm==4.68.3
|
||||
transformers==5.14.1
|
||||
triton==3.4.0
|
||||
typepy==1.3.5
|
||||
typer==0.27.0
|
||||
typing-extensions==4.15.0
|
||||
typing-inspection==0.4.2
|
||||
tzdata==2026.2
|
||||
urllib3==2.5.0
|
||||
wcwidth==0.8.1
|
||||
word2number==1.1
|
||||
xxhash==3.8.1
|
||||
275740
tokenizer.json
Normal file
275740
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
17
tokenizer_config.json
Normal file
17
tokenizer_config.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"add_prefix_space": true,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"is_local": false,
|
||||
"legacy": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "TokenizersBackend",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user