You can deploy this model and start earning money today!

RichardErkhov/
m8than_-_mistral-7b-instruct-0.2-gguf

Name: m8than_-_mistral-7b-instruct-0.2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mistral-7b-instruct-0.2 - GGUF

Model creator: https://huggingface.co/m8than/
Original model: https://huggingface.co/m8than/mistral-7b-instruct-0.2/

Name	Quant method	Size
mistral-7b-instruct-0.2.Q2_K.gguf	Q2_K	2.53GB
mistral-7b-instruct-0.2.IQ3_XS.gguf	IQ3_XS	2.81GB
mistral-7b-instruct-0.2.IQ3_S.gguf	IQ3_S	2.96GB
mistral-7b-instruct-0.2.Q3_K_S.gguf	Q3_K_S	2.95GB
mistral-7b-instruct-0.2.IQ3_M.gguf	IQ3_M	3.06GB
mistral-7b-instruct-0.2.Q3_K.gguf	Q3_K	3.28GB
mistral-7b-instruct-0.2.Q3_K_M.gguf	Q3_K_M	3.28GB
mistral-7b-instruct-0.2.Q3_K_L.gguf	Q3_K_L	3.56GB
mistral-7b-instruct-0.2.IQ4_XS.gguf	IQ4_XS	3.67GB
mistral-7b-instruct-0.2.Q4_0.gguf	Q4_0	3.83GB
mistral-7b-instruct-0.2.IQ4_NL.gguf	IQ4_NL	3.87GB
mistral-7b-instruct-0.2.Q4_K_S.gguf	Q4_K_S	3.86GB
mistral-7b-instruct-0.2.Q4_K.gguf	Q4_K	4.07GB
mistral-7b-instruct-0.2.Q4_K_M.gguf	Q4_K_M	1.06GB
mistral-7b-instruct-0.2.Q4_1.gguf	Q4_1	0.21GB
mistral-7b-instruct-0.2.Q5_0.gguf	Q5_0	4.65GB
mistral-7b-instruct-0.2.Q5_K_S.gguf	Q5_K_S	4.65GB
mistral-7b-instruct-0.2.Q5_K.gguf	Q5_K	4.78GB
mistral-7b-instruct-0.2.Q5_K_M.gguf	Q5_K_M	4.78GB
mistral-7b-instruct-0.2.Q5_1.gguf	Q5_1	5.07GB
mistral-7b-instruct-0.2.Q6_K.gguf	Q6_K	5.53GB
mistral-7b-instruct-0.2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 tags:

finetuned pipeline_tag: text-generation inference: true widget:
messages:
- role: user content: What is your favorite condiment?

extra_gated_description: If you want to learn more about how we process your personal data, please read our Privacy Policy.

Model Card for Mistral-7B-Instruct-v0.2

Encode and Decode with `mistral_common`

from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.protocol.instruct.messages import UserMessage
from mistral_common.protocol.instruct.request import ChatCompletionRequest
 
mistral_models_path = "MISTRAL_MODELS_PATH"
 
tokenizer = MistralTokenizer.v1()
 
completion_request = ChatCompletionRequest(messages=[UserMessage(content="Explain Machine Learning to me in a nutshell.")])
 
tokens = tokenizer.encode_chat_completion(completion_request).tokens

Inference with `mistral_inference`

from mistral_inference.model import Transformer
from mistral_inference.generate import generate

model = Transformer.from_folder(mistral_models_path)
out_tokens, _ = generate([tokens], model, max_tokens=64, temperature=0.0, eos_id=tokenizer.instruct_tokenizer.tokenizer.eos_id)

result = tokenizer.decode(out_tokens[0])

print(result)

Inference with hugging face `transformers`

from transformers import AutoModelForCausalLM
 
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
model.to("cuda")
 
generated_ids = model.generate(tokens, max_new_tokens=1000, do_sample=True)

# decode with mistral tokenizer
result = tokenizer.decode(generated_ids[0].tolist())
print(result)

[!TIP] PRs to correct the transformers tokenizer so that it gives 1-to-1 the same results as the mistral_common reference implementation are very welcome!

The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.

Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1

32k context window (vs 8k context in v0.1)
Rope-theta = 1e6
No Sliding-Window Attention

For full details of this model please read our paper and release blog post.

Instruction format

In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST] and [/INST] tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.

E.g.

text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"

This format is available as a chat template via the apply_chat_template() method:

python

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Troubleshooting

If you see the following error:

Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'

Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers

This should not be required after transformers-v4.33.4.

Limitations

The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.

The Mistral AI Team

Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

RichardErkhov/m8than_-_mistral-7b-instruct-0.2-gguf